© 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. 7-RES-JB
    11. 20642
    Prev
    Next
    INDEX
    Explanations

    sequences of mixed characters, likely computer code or other forms of structured data

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric sequences or character combinations

    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
     msec
    -0.67
    DonaldTrump
    -0.67
     derog
    -0.66
    Attempts
    -0.62
     describe
    -0.58
     shorth
    -0.58
     abbrevi
    -0.58
     cardboard
    -0.58
     slightest
    -0.57
     suffering
    -0.55
    POSITIVE LOGITS
    XM
    0.93
    qq
    0.87
    Iv
    0.82
    _-
    0.82
    FK
    0.81
    ZX
    0.77
    dq
    0.76
    JJ
    0.76
    wk
    0.75
    Q
    0.75
    Activations Density 0.028%

    No Known Activations