© 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. 8-RES-JB
    11. 6809
    Prev
    Next
    INDEX
    Explanations

    comparisons or statistical relationships between different groups or attributes

    oai_token-act-pair · gpt-3.5-turbo

    comparisons indicating disadvantage or inferiority in statistics

    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
    rend
    -0.72
    uto
    -0.67
    oola
    -0.65
    ista
    -0.64
     reperc
    -0.63
    ocalypse
    -0.63
    ternity
    -0.61
     shenan
    -0.60
     revelation
    -0.57
     Revelations
    -0.57
    POSITIVE LOGITS
     others
    0.84
     usual
    0.82
     counterparts
    0.81
     comparable
    0.81
    average
    0.79
     peers
    0.77
     average
    0.75
     untreated
    0.75
     those
    0.75
     traditional
    0.75
    Activations Density 0.112%

    No Known Activations