© 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. 4201
    Prev
    Next
    INDEX
    Explanations

    references to administrative roles or tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to administrative roles or functions

    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
    BSD
    -0.94
     Flavoring
    -0.83
    Unity
    -0.82
    RIC
    -0.80
    DragonMagazine
    -0.79
    ĺħ
    -0.78
    OX
    -0.77
    ãĤ½
    -0.75
    version
    -0.74
    ovie
    -0.73
    POSITIVE LOGITS
    ..
    0.99
     âĢ
    0.76
     ..
    0.74
     restraint
    0.70
     Calder
    0.70
     evid
    0.69
     Amit
    0.68
     Admin
    0.67
     prescribed
    0.64
     Daly
    0.63
    Activations Density 0.001%

    No Known Activations