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. 9-RES-JB
    6. 20378
    Prev
    Next
    INDEX
    Explanations

    names of individuals, including political figures

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply time or temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sisters
    -0.84
     girls
    -0.77
     sister
    -0.76
     femin
    -0.76
    cca
    -0.73
     women
    -0.72
    ona
    -0.72
     nuns
    -0.71
    wcs
    -0.68
     females
    -0.68
    POSITIVE LOGITS
    Mr
    1.20
    His
    1.15
    He
    1.09
     Mr
    1.09
     Manziel
    1.02
     He
    1.01
    iannopoulos
    0.95
    HAEL
    0.93
     he
    0.92
     His
    0.92
    Activations Density 1.130%

    No Known Activations