© 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. 11-RES-JB
    11. 10000
    Prev
    Next
    INDEX
    Explanations

    acronym "AFP" which is usually associated with news agencies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "AFP" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ths
    -0.79
    stood
    -0.78
    hands
    -0.75
    ials
    -0.74
    iates
    -0.71
    oops
    -0.68
    hips
    -0.67
    hal
    -0.67
    chest
    -0.67
    tons
    -0.66
    POSITIVE LOGITS
     PHOTO
    1.06
    UTERS
    0.96
    TN
    0.76
    ERC
    0.75
    pload
    0.73
    NEWS
    0.71
    DEF
    0.70
     NEWS
    0.70
     Photo
    0.70
    /
    0.67
    Activations Density 0.023%

    No Known Activations