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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1475
    Prev
    Next
    INDEX
    Explanations

    degrees (temperature measurements)

    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
    288
    +0.16
    0.5%
    195
    +0.16
    0.5%
    198
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.04
    647
    +0.16
    0.03
    109
    +0.15
    0.03
    Negative Logits
    sels
    -1.14
    ded
    -1.10
    theless
    -1.07
     Bans
    -1.04
    geist
    -1.02
    oids
    -0.99
    IUM
    -0.99
    atro
    -0.98
     Pengu
    -0.96
    BAT
    -0.95
    POSITIVE LOGITS
     Celsius
    1.53
     Fahrenheit
    1.42
    rees
    1.39
     degrees
    1.32
     degree
    1.18
     Degree
    1.13
    uates
    1.11
     Deg
    1.06
     curve
    1.03
    renheit
    1.02
    Activations Density 0.380%

    No Known Activations