© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 4288
    Prev
    Next
    INDEX
    Explanations

    terms related to a direction, either physical or metaphorical

    oai_token-act-pair · gpt-3.5-turbo

    references to decisions and the consequences of choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -0.76
    rities
    -0.73
    abilia
    -0.72
    iencies
    -0.71
    chens
    -0.70
    nice
    -0.70
    unts
    -0.70
    auna
    -0.70
    ombies
    -0.68
    iuses
    -0.67
    POSITIVE LOGITS
     toward
    1.13
     towards
    1.09
     tread
    0.97
     direction
    0.95
     directions
    0.92
     paths
    0.89
     footsteps
    0.88
     trajectory
    0.86
     Directions
    0.86
     downward
    0.82
    Activations Density 0.355%

    No Known Activations