© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 46034
    Prev
    Next
    INDEX
    Explanations

    text related to sports drafts and player selections

    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
    +0.19
    0.7%
    288
    +0.15
    0.6%
    554
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    735
    +0.19
    0.06
    256
    +0.15
    0.06
    651
    +0.14
    0.07
    Negative Logits
     membr
    -0.89
     lapt
    -0.85
     encount
    -0.84
    pour
    -0.81
    onse
    -0.80
    ĸļ
    -0.80
    borough
    -0.79
     Glac
    -0.79
    oeuv
    -0.77
     interf
    -0.76
    POSITIVE LOGITS
    smanship
    1.54
    Kings
    1.36
     lottery
    1.14
     picks
    1.14
     Picks
    1.08
     combine
    0.93
     dod
    0.91
    Express
    0.91
    raft
    0.87
    aways
    0.86
    Activations Density 5.173%

    No Known Activations