© 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. 11-RES-JB
    11. 18733
    Prev
    Next
    INDEX
    Explanations

    years and centuries

    oai_token-act-pair · gpt-3.5-turbo

    historical dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppable
    -0.82
    malink
    -0.75
    arty
    -0.75
    grass
    -0.72
    ynthesis
    -0.66
    gment
    -0.65
    ynchronous
    -0.65
    unal
    -0.62
     treadmill
    -0.61
    insky
    -0.60
    POSITIVE LOGITS
     BCE
    1.66
     BC
    1.51
     CE
    1.50
     AD
    1.42
    AD
    1.35
    BC
    1.33
     AH
    1.15
     bc
    1.09
     BB
    1.03
     AE
    1.01
    Activations Density 0.062%

    No Known Activations