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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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 Local
    5. 6-RES_SCL-AJT
    6. 13182
    Prev
    Next
    INDEX
    Explanations

    descriptions of mythical creatures and magical battles

    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
    647
    +0.02
    0.5%
    484
    +0.02
    0.4%
    262
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.02
    0.55
    6
    +0.02
    0.30
    255
    +0.02
    0.21
    Negative Logits
    yip
    -0.15
     Tackle
    -0.14
     parasite
    -0.13
    wich
    -0.13
    onica
    -0.13
    ugh
    -0.13
    borough
    -0.13
    ¿½
    -0.13
    nut
    -0.13
     Craw
    -0.13
    POSITIVE LOGITS
    quished
    0.18
    GROUND
    0.14
    Ü
    0.13
    verse
    0.13
     prominently
    0.13
     laureate
    0.13
    ordon
    0.13
    ----------
    0.12
    --------------------------------------------------------
    0.12
    DragonMagazine
    0.12
    Activations Density 21.160%

    No Known Activations