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. 7-RES-JB
    6. 14888
    Prev
    Next
    INDEX
    Explanations

    explicitly marked phrases or clauses within the text

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or pauses in the text that suggest significant or incomplete thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.76
    appa
    -0.74
    ãĥ«
    -0.72
     charms
    -0.70
     cabbage
    -0.65
     liner
    -0.64
     Vegeta
    -0.63
     ring
    -0.63
    Ĭ±
    -0.63
     grate
    -0.63
    POSITIVE LOGITS
    etc
    0.88
    incre
    0.86
    emb
    0.82
    eas
    0.81
    these
    0.80
    among
    0.79
    there
    0.79
    having
    0.78
    Coun
    0.78
    [
    0.78
    Activations Density 0.035%

    No Known Activations