Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4048
    Prev
    Next
    INDEX
    Explanations

    names and labels related to specific entities, as well as specific historical and technical terms

    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
    153
    +0.19
    0.6%
    99
    +0.18
    0.6%
    527
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.19
    0.07
    659
    +0.18
    0.06
    232
    +0.17
    0.05
    Negative Logits
    hips
    -1.29
    loo
    -1.27
     bearer
    -1.16
    AGES
    -1.09
    DragonMagazine
    -1.06
    ãĥ¼ãĥĨãĤ£
    -1.04
    andise
    -0.97
    ional
    -0.96
    DOWN
    -0.95
    cake
    -0.95
    POSITIVE LOGITS
    arest
    1.66
    verend
    1.44
    braska
    1.38
    olithic
    1.37
    arthed
    1.20
    uter
    1.19
    umann
    1.17
    zi
    1.14
    cker
    1.14
    jad
    1.11
    Activations Density 1.108%

    No Known Activations