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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 17077
    Prev
    Next
    INDEX
    Explanations

    references to updating or documents being kept online

    oai_token-act-pair · gpt-3.5-turbo

    mentions of updates or changes to records or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rated
    -1.02
     Inquisition
    -0.66
     Aber
    -0.65
     Rapid
    -0.65
     Aim
    -0.64
     Shots
    -0.64
     pinch
    -0.63
     Sharp
    -0.63
     Barg
    -0.63
    ENDED
    -0.62
    POSITIVE LOGITS
    din
    0.76
    edom
    0.65
    Entity
    0.65
     transcend
    0.65
    ĺħ
    0.64
    birds
    0.64
    immigrant
    0.64
    warts
    0.63
    cair
    0.63
    nut
    0.62
    Activations Density 0.000%

    No Known Activations