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. 8-RES-JB
    6. 22973
    Prev
    Next
    INDEX
    Explanations

    words related to the action of arriving or reaching a certain state or condition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "come" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.76
    tops
    -0.74
    rollers
    -0.71
    orthodox
    -0.70
    skirts
    -0.70
    cius
    -0.69
    ruff
    -0.69
    roller
    -0.68
    ¥µ
    -0.67
    orsi
    -0.67
    POSITIVE LOGITS
     undone
    0.99
     forth
    0.96
     hither
    0.83
     apart
    0.82
     ashore
    0.77
     Forth
    0.75
     into
    0.74
     together
    0.73
     back
    0.73
     up
    0.73
    Activations Density 0.065%

    No Known Activations