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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 84
    Prev
    Next
    INDEX
    Explanations

    descriptions of activities or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or pauses in text, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    untarily
    -0.70
    chan
    -0.67
    liest
    -0.65
    enary
    -0.64
    gaard
    -0.64
    ppo
    -0.63
    opt
    -0.61
    olo
    -0.61
    forth
    -0.60
    iple
    -0.60
    POSITIVE LOGITS
     including
    0.97
     namely
    0.95
     albeit
    0.94
     which
    0.94
     reminiscent
    0.93
     akin
    0.93
     aka
    0.90
     huh
    0.90
     consisting
    0.90
     especially
    0.89
    Activations Density 0.484%

    No Known Activations