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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 10211
    Prev
    Next
    INDEX
    Explanations

    past participles of verbs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "had been" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]);
    -0.66
    Mario
    -0.65
     taxp
    -0.64
    RIP
    -0.63
    hovah
    -0.62
    Rap
    -0.62
    cious
    -0.62
     salute
    -0.62
    +)
    -0.62
    index
    -0.61
    POSITIVE LOGITS
     earlier
    0.92
     previously
    0.89
    keyes
    0.79
     hoped
    0.78
     exha
    0.74
     originally
    0.71
    iless
    0.69
     previous
    0.69
    foreseen
    0.67
     looph
    0.67
    Activations Density 0.263%

    No Known Activations