© 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. 4-RES-JB
    11. 14804
    Prev
    Next
    INDEX
    Explanations

    phrases related to fandom or community involvement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of diasporas and fandoms

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

    No Comments

    Negative Logits
    bats
    -0.69
    iasis
    -0.69
     dams
    -0.68
     deduct
    -0.66
    ptive
    -0.66
    urers
    -0.62
     towers
    -0.62
    nered
    -0.60
     deceive
    -0.60
     lookout
    -0.60
    POSITIVE LOGITS
    pora
    1.15
     fandom
    0.78
    Reader
    0.73
     Roots
    0.71
     fanbase
    0.70
    Tang
    0.68
    rosso
    0.67
    culture
    0.67
     Diary
    0.67
    Wiki
    0.67
    Activations Density 0.044%

    No Known Activations