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. 11-RES-JB
    6. 7365
    Prev
    Next
    INDEX
    Explanations

    references to technical data formats, such as file extensions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the AC/DC band or related references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extermin
    -0.77
     swe
    -0.75
     reve
    -0.73
     creep
    -0.73
     plants
    -0.71
     sooner
    -0.70
     accus
    -0.70
     tighter
    -0.70
     retard
    -0.69
     lic
    -0.69
    POSITIVE LOGITS
    CN
    1.20
    ãĥīãĥ©ãĤ´ãĥ³
    1.19
    ANI
    1.18
    AFP
    1.18
    RH
    1.15
    Pg
    1.11
    OSS
    1.11
    Flickr
    1.10
    UTC
    1.09
    UX
    1.09
    Activations Density 0.043%

    No Known Activations