© 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. 18530
    Prev
    Next
    INDEX
    Explanations

    advertisement-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertisements

    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
    assic
    -0.75
     gorilla
    -0.65
     mates
    -0.64
     ecstasy
    -0.62
    mate
    -0.61
     Lans
    -0.61
     marsh
    -0.61
    gran
    -0.60
     subsistence
    -0.59
     Dull
    -0.58
    POSITIVE LOGITS
    Skip
    0.89
    Comments
    0.79
    ROR
    0.77
    Images
    0.76
    VERTISEMENT
    0.76
     Thumbnails
    0.75
     Stories
    0.72
     Subscribe
    0.72
     Continue
    0.71
     Links
    0.70
    Activations Density 0.023%

    No Known Activations