© 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. 2723
    Prev
    Next
    INDEX
    Explanations

    negative descriptions of various concepts or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to the science fiction genre

    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
     Duchess
    -0.73
     Clerk
    -0.65
     Holt
    -0.64
     Clintons
    -0.64
     Roose
    -0.62
     Downing
    -0.62
    ADRA
    -0.62
     blush
    -0.62
     Rost
    -0.62
     Chains
    -0.62
    POSITIVE LOGITS
    fi
    1.26
    sci
    1.14
    Fi
    1.00
    fiction
    0.98
    tech
    0.92
    ê
    0.89
     fi
    0.85
    inspired
    0.84
    technical
    0.83
    engineering
    0.81
    Activations Density 0.022%

    No Known Activations