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. 9-RES-JB
    6. 8118
    Prev
    Next
    INDEX
    Explanations

    phrases related to names and titles

    oai_token-act-pair · gpt-3.5-turbo
    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
     etc
    -0.94
     didnt
    -0.74
    +,
    -0.68
     mins
    -0.66
     dont
    -0.66
    +.
    -0.63
     folks
    -0.63
    abouts
    -0.63
     blogs
    -0.63
     doesnt
    -0.63
    POSITIVE LOGITS
     Canaver
    1.05
    ãĤ¢ãĥ«
    0.72
    onement
    0.69
    osate
    0.69
    amel
    0.68
     Franz
    0.67
    ãĥīãĥ©
    0.64
    aterasu
    0.64
     circumcision
    0.62
     Adin
    0.62
    Activations Density 1.520%

    No Known Activations