© 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. 1-RES-JB
    11. 23111
    Prev
    Next
    INDEX
    Explanations

    number sequences

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly in the format of prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igating
    -0.90
     ingred
    -0.81
     satell
    -0.78
     glim
    -0.78
    attled
    -0.77
    irlf
    -0.76
    antha
    -0.75
     hung
    -0.71
    ngth
    -0.69
    igators
    -0.67
    POSITIVE LOGITS
    999
    1.34
    99
    1.12
    79
    1.01
    88
    1.00
    98
    0.97
    89
    0.97
    91
    0.96
    97
    0.95
    49
    0.94
    67
    0.91
    Activations Density 0.017%

    No Known Activations