© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2727
    Prev
    Next
    INDEX
    Explanations

    highly frequent proper nouns or entities, especially with repeating patterns in their names

    oai_token-act-pair · gpt-3.5-turbo

    references to various media entities and news sources

    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
     deduct
    -0.74
     additionally
    -0.73
     craw
    -0.73
     dece
    -0.71
     tram
    -0.70
     triv
    -0.69
     bundled
    -0.69
     larvae
    -0.68
     princ
    -0.68
     aggreg
    -0.67
    POSITIVE LOGITS
    Dear
    1.29
    Former
    1.23
    SAN
    1.21
    LOS
    1.20
    WASHINGTON
    1.20
    Published
    1.18
    When
    1.15
    If
    1.14
    Whether
    1.14
    TOR
    1.14
    Activations Density 0.208%

    No Known Activations