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

    Neuronpedia

    Jacobian LensNEW
    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 Local
    5. 6-RES_SCL-AJT
    6. 34911
    Prev
    Next
    INDEX
    Explanations

    phrases related to freedom of speech, political debates, and opinions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.30
    1.5%
    92
    +0.11
    0.6%
    360
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.30
    0.23
    288
    +0.11
    0.33
    1
    +0.10
    0.14
    Negative Logits
    JV
    -0.57
    ucky
    -0.57
    leases
    -0.56
    negie
    -0.56
    olulu
    -0.54
    ortium
    -0.54
    ymm
    -0.54
    oda
    -0.54
    nar
    -0.53
    ajor
    -0.53
    POSITIVE LOGITS
    telling
    0.69
    ynthesis
    0.69
    ifice
    0.64
    LAB
    0.63
    uration
    0.63
     Obj
    0.63
    icial
    0.60
    bol
    0.60
    pload
    0.60
     answ
    0.60
    Activations Density 22.722%

    No Known Activations