© 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. 7-RES-JB
    11. 1469
    Prev
    Next
    INDEX
    Explanations

    numerical patterns possibly related to a specific programming language or code sequence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'x' and its variations or representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pru
    -0.81
    zona
    -0.76
     Garry
    -0.75
    sburgh
    -0.74
    assetsadobe
    -0.74
     TODAY
    -0.72
    getic
    -0.71
    DERR
    -0.71
    kamp
    -0.70
    maid
    -0.69
    POSITIVE LOGITS
    aminer
    0.96
    ------
    0.84
    Ry
    0.84
    avier
    0.83
    actly
    0.83
    amination
    0.82
    posed
    0.80
    arb
    0.78
    iii
    0.78
    anth
    0.77
    Activations Density 0.024%

    No Known Activations