© 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. 1553
    Prev
    Next
    INDEX
    Explanations

    phrases related to speculation or possibility

    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
    195
    +0.20
    0.7%
    68
    +0.16
    0.5%
    551
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.20
    0.08
    278
    +0.16
    0.07
    114
    +0.16
    0.06
    Negative Logits
    ging
    -1.16
     Fighter
    -1.02
    performing
    -1.00
    pires
    -0.95
     Enforcement
    -0.93
    raint
    -0.93
    feeding
    -0.92
    ocracy
    -0.91
    rency
    -0.90
    fight
    -0.90
    POSITIVE LOGITS
    onna
    1.42
    haps
    1.31
    hap
    1.30
     be
    1.20
    bes
    1.16
     optionally
    1.06
    entimes
    1.04
     confuse
    1.04
     elect
    1.04
     misunder
    1.03
    Activations Density 0.657%

    No Known Activations