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. 9-RES-JB
    6. 9638
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'vent' with varying forms and contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "vent" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hitman
    -0.70
    UTERS
    -0.67
    makers
    -0.63
     Kerry
    -0.63
    lihood
    -0.62
    maker
    -0.62
     Manit
    -0.60
     Cuomo
    -0.60
     phosphate
    -0.59
    FT
    -0.56
    POSITIVE LOGITS
    ricular
    1.48
    urous
    1.38
    ilated
    1.33
    uring
    1.31
    ilation
    1.28
    rue
    1.14
    ral
    1.12
    uri
    1.09
    urers
    1.05
    uras
    1.02
    Activations Density 0.052%

    No Known Activations