© 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. 10-RES-JB
    11. 6744
    Prev
    Next
    INDEX
    Explanations

    words related to successful or unsuccessful outcomes or results

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "work" or its variants, indicating discussions about workability or effectiveness of strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anamo
    -0.85
    antha
    -0.81
    ailable
    -0.74
    sbm
    -0.66
    76561
    -0.64
    pora
    -0.64
    ople
    -0.63
    xual
    -0.63
     Browse
    -0.62
    gart
    -0.62
    POSITIVE LOGITS
     wonders
    1.32
     miracles
    1.18
    heet
    1.09
     harder
    0.96
     overtime
    0.93
     tirelessly
    0.92
     flaw
    0.92
    bench
    0.92
     brilliantly
    0.91
     against
    0.91
    Activations Density 0.051%

    No Known Activations