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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9996
    Prev
    Next
    INDEX
    Explanations

    locations, institutions, or objects that are the same or identical

    oai_token-act-pair · gpt-3.5-turbo

    references to shared experiences or commonalities

    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
    cknowled
    -0.64
     Uriel
    -0.60
    cknow
    -0.56
     Gau
    -0.56
     candid
    -0.54
    hen
    -0.53
    tiny
    -0.53
     palp
    -0.53
     TAG
    -0.52
     Wiki
    -0.52
    POSITIVE LOGITS
    nings
    0.76
    iatus
    0.72
    kefeller
    0.71
    same
    0.68
    ozo
    0.67
    rant
    0.65
    ulative
    0.65
    vier
    0.65
    amazon
    0.65
     Tradable
    0.63
    Activations Density 0.148%

    No Known Activations