© 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 EvalsExportsinterp-engineNEWAPI 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. 14443
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns in a series of events or numbers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sequences or patterns in various contexts

    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
    sburgh
    -0.88
    ryn
    -0.85
    fman
    -0.76
    lying
    -0.75
    sie
    -0.75
    isle
    -0.75
    aneers
    -0.74
    aghd
    -0.73
    enthal
    -0.73
    nai
    -0.71
    POSITIVE LOGITS
     Sequence
    0.93
     sequence
    0.84
     sequences
    0.83
     unfold
    0.79
    uality
    0.77
     repeats
    0.75
    ĸļ
    0.71
     unfolds
    0.69
    alysis
    0.65
    eers
    0.64
    Activations Density 0.030%

    No Known Activations