© 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. 1241
    Prev
    Next
    INDEX
    Explanations

    phrases related to progression or development

    oai_token-act-pair · gpt-3.5-turbo

    references to specific programming-related terms or names

    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
    Ton
    -0.80
     Dawson
    -0.78
    ahime
    -0.75
    ila
    -0.70
    Items
    -0.68
    andal
    -0.67
    Salt
    -0.67
    andum
    -0.66
     Lauderdale
    -0.66
    zzle
    -0.66
    POSITIVE LOGITS
     prog
    4.05
     prot
    1.05
     Pred
    1.05
     PROG
    0.97
     Zerg
    0.92
     doom
    0.92
     prediction
    0.91
     proto
    0.91
     constitu
    0.90
     precursor
    0.89
    Activations Density 0.014%

    No Known Activations