© 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 Local
    5. 6-RES_SCL-AJT
    6. 4847
    Prev
    Next
    INDEX
    Explanations

    words related to emotional experiences like feasting, feigning, loyalty, and sacrificing

    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
    99
    +0.07
    0.5%
    97
    +0.06
    0.5%
    598
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.07
    0.21
    288
    +0.06
    0.20
    271
    +0.06
    0.05
    Negative Logits
    helle
    -0.45
    onto
    -0.42
    assian
    -0.41
    UTH
    -0.41
    AGE
    -0.40
    issors
    -0.40
    Fill
    -0.39
    atchewan
    -0.38
    âĹ¼
    -0.38
    adium
    -0.38
    POSITIVE LOGITS
     fe
    0.53
    erate
    0.53
    ldom
    0.51
    eful
    0.48
    esses
    0.47
    emaker
    0.43
    fare
    0.43
    eb
    0.42
    efully
    0.42
    ruary
    0.42
    Activations Density 7.865%

    No Known Activations