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. 6-RES-JB
    6. 16374
    Prev
    Next
    INDEX
    Explanations

    words related to equipment or tools

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the end-of-text token, indicating document termination or completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.64
    eatures
    -0.62
    ·
    -0.62
    ãĥİ
    -0.62
    ®
    -0.60
    escription
    -0.59
    IJ
    -0.59
    ikuman
    -0.59
    efully
    -0.58
    POSITIVE LOGITS
     Earthqu
    0.47
    !
    0.46
     guiName
    0.46
    :
    0.44
     Insp
    0.44
     Converted
    0.43
    ,
    0.43
     joke
    0.43
    !,
    0.42
     [
    0.42
    Activations Density 1.506%

    No Known Activations