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. 8-RES-JB
    6. 3471
    Prev
    Next
    INDEX
    Explanations

    phrases with periods at the end

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     biod
    -0.59
     whistleblowers
    -0.58
     confidentiality
    -0.57
     privacy
    -0.56
     deceptive
    -0.55
     outgoing
    -0.54
     safety
    -0.53
     aborted
    -0.53
     victims
    -0.53
    izons
    -0.52
    POSITIVE LOGITS
    imgur
    1.02
    e
    0.81
    hat
    0.71
    MX
    0.71
    seed
    0.70
    aca
    0.70
    Lenin
    0.70
    degree
    0.69
    minimum
    0.68
    hs
    0.64
    Activations Density 0.028%

    No Known Activations