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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14523
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format, such as 'MM.DD' with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    versions of the Ubuntu operating system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reluct
    -0.76
    Þ
    -0.72
    ocene
    -0.71
     strugg
    -0.66
    tones
    -0.65
     appropriation
    -0.63
     streng
    -0.63
    appropri
    -0.63
    ãĤ±
    -0.62
    utherland
    -0.61
    POSITIVE LOGITS
    00
    0.97
    003
    0.91
    004
    0.86
    01
    0.84
    02
    0.78
    raction
    0.78
    04
    0.78
    03
    0.78
    27
    0.77
    005
    0.76
    Activations Density 0.014%

    No Known Activations