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. 4350
    Prev
    Next
    INDEX
    Explanations

    numerical codes or technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific identifiers related to data metrics

    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
    di
    -0.84
     Dixon
    -0.80
    261
    -0.75
    iph
    -0.73
     OD
    -0.73
    rh
    -0.73
    IB
    -0.72
    inth
    -0.72
    iosis
    -0.72
    DI
    -0.71
    POSITIVE LOGITS
    00
    1.05
    Į
    0.95
    ->
    0.95
     ->
    0.90
    005
    0.86
    ":["
    0.84
    -->
    0.84
    aler
    0.82
    004
    0.81
    IJ
    0.81
    Activations Density 0.373%

    No Known Activations