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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17877
    Prev
    Next
    INDEX
    Explanations

    Words related to specific actions or processes involving physical movement or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases that indicate relationships among ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iciary
    -0.71
    ortium
    -0.69
     sponsor
    -0.68
     Lerner
    -0.67
     issuer
    -0.66
     publisher
    -0.65
     Sloan
    -0.64
    arlane
    -0.63
     Thomson
    -0.63
     slate
    -0.62
    POSITIVE LOGITS
    Downloadha
    0.75
    tons
    0.74
    rams
    0.72
    Integ
    0.72
     stunts
    0.71
    Quotes
    0.71
    pause
    0.70
    Pattern
    0.69
    argon
    0.68
    nee
    0.67
    Activations Density 0.668%

    No Known Activations