© 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. 6787
    Prev
    Next
    INDEX
    Explanations

    email opt-in information and newsletters from a particular source

    oai_token-act-pair · gpt-3.5-turbo

    references to news sources and their content

    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
    ilts
    -0.75
    itled
    -0.68
    icum
    -0.64
    boa
    -0.63
    issors
    -0.63
    idth
    -0.63
    Reviewed
    -0.62
    auga
    -0.62
    imeo
    -0.61
    ittance
    -0.61
    POSITIVE LOGITS
     BBC
    0.67
    rish
    0.63
     giveaways
    0.62
     POLITICO
    0.61
     UNHCR
    0.61
    eric
    0.59
     NPR
    0.59
     Outlook
    0.59
     FIGHT
    0.58
     Etsy
    0.58
    Activations Density 0.049%

    No Known Activations