© 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. 20292
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, potentially celebrities or public figures

    oai_token-act-pair · gpt-3.5-turbo

    names of musical artists or contributors

    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
     Sprint
    -0.76
    perse
    -0.74
    Saharan
    -0.73
    lean
    -0.70
    oral
    -0.69
     slavery
    -0.69
    omen
    -0.69
    hoe
    -0.68
     scaven
    -0.66
     upstream
    -0.65
    POSITIVE LOGITS
     Wiz
    4.39
     Kom
    1.18
    dj
    1.17
     Aur
    1.13
     QC
    1.08
     Sly
    0.96
    MJ
    0.95
     fuzz
    0.95
     Kop
    0.94
     DM
    0.92
    Activations Density 0.040%

    No Known Activations