© 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. 4-RES-JB
    11. 14802
    Prev
    Next
    INDEX
    Explanations

    references to large scale or significant events or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to large-scale or significant events, impacts, or quantities

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

    No Comments

    Negative Logits
    yer
    -0.84
    tein
    -0.78
    ople
    -0.74
    lest
    -0.73
    wich
    -0.73
    gemony
    -0.71
    keeper
    -0.70
    wick
    -0.69
    akers
    -0.69
    arers
    -0.69
    POSITIVE LOGITS
     amounts
    1.16
     earthqu
    1.04
     undertaking
    0.96
     influx
    0.94
     quantities
    0.91
     amount
    0.89
     swath
    0.86
     disproportion
    0.85
     proportions
    0.81
     chunk
    0.81
    Activations Density 0.029%

    No Known Activations