© 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. 0-RES-JB
    11. 22242
    Prev
    Next
    INDEX
    Explanations

    mentions of fans or fandom

    oai_token-act-pair · gpt-3.5-turbo

    words associated with fandom and fans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normandy
    -0.79
     OB
    -0.68
     days
    -0.66
     pear
    -0.64
     reproductive
    -0.64
     vulnerable
    -0.64
     bodies
    -0.64
     ounces
    -0.64
     Est
    -0.63
     Marble
    -0.63
    POSITIVE LOGITS
    fan
    4.28
    Fan
    2.51
     Fan
    1.76
     fan
    1.72
    Fans
    1.51
     Fans
    1.51
     fanatic
    1.30
    andom
    1.28
     fans
    1.28
     fandom
    1.28
    Activations Density 0.013%

    No Known Activations