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. 45229
    Prev
    Next
    INDEX
    Explanations

    phrases related to past events or long-standing traditions

    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
    +0.10
    1.0%
    144
    +0.05
    0.5%
    536
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.17
    608
    +0.05
    0.20
    95
    +0.05
    0.06
    Negative Logits
    Stars
    -0.40
    daq
    -0.39
    atures
    -0.38
    illions
    -0.38
    hammad
    -0.35
    ageddon
    -0.35
    imble
    -0.35
    amera
    -0.35
    isites
    -0.34
    rophic
    -0.33
    POSITIVE LOGITS
     resident
    0.44
     longtime
    0.40
     acquaintance
    0.40
     staple
    0.39
    stay
    0.37
     collaborator
    0.37
     associate
    0.37
     favourite
    0.37
     memory
    0.36
     favorite
    0.36
    Activations Density 9.088%

    No Known Activations