© 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. 34885
    Prev
    Next
    INDEX
    Explanations

    information relating to distance, specifically the word 'far' used in different contexts

    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
    +0.18
    0.7%
    187
    +0.14
    0.5%
    441
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.18
    0.06
    736
    +0.14
    0.07
    55
    +0.14
    0.09
    Negative Logits
    emis
    -0.99
    piracy
    -0.91
    ptive
    -0.86
     Picks
    -0.84
    icks
    -0.83
    ysis
    -0.83
    ription
    -0.81
    ellation
    -0.81
    emy
    -0.80
    ycle
    -0.80
    POSITIVE LOGITS
    thing
    1.25
    med
    1.13
    fetched
    1.11
     enough
    1.10
    itud
    0.95
    aday
    0.94
    entimes
    0.91
     Enough
    0.91
    enough
    0.91
    zx
    0.89
    Activations Density 6.874%

    No Known Activations