© 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. 0-RES-JB
    11. 19321
    Prev
    Next
    INDEX
    Explanations

    references to statistical data points within sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aque
    -0.77
    atom
    -0.74
    ilateral
    -0.73
    lie
    -0.69
    Published
    -0.67
    asonic
    -0.65
    ë
    -0.65
    ee
    -0.64
     accommod
    -0.64
     conveyed
    -0.64
    POSITIVE LOGITS
     stats
    3.61
    stats
    2.49
     Stats
    2.46
     statistics
    2.43
    Stats
    2.07
     stat
    1.93
    Statistics
    1.88
     STATS
    1.78
     metrics
    1.76
     statistic
    1.72
    Activations Density 0.013%

    No Known Activations