© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14243
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to different individuals, such as names of people or places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    247
    +0.19
    0.7%
    285
    +0.17
    0.6%
    575
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.05
    232
    +0.17
    0.04
    659
    +0.14
    0.04
    Negative Logits
    è¦ļéĨĴ
    -1.37
    atform
    -1.15
    ramid
    -1.02
    rooms
    -0.99
    hematic
    -0.94
    Discussion
    -0.85
    DERR
    -0.84
    teen
    -0.83
     variance
    -0.82
     externalToEVAOnly
    -0.81
    POSITIVE LOGITS
    vironment
    1.57
    ews
    1.33
    cia
    1.21
    icidal
    1.15
    culosis
    1.14
    flix
    1.12
    elist
    1.10
    stadt
    1.07
    viron
    1.07
    esse
    1.07
    Activations Density 0.630%

    No Known Activations