© 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. 24067
    Prev
    Next
    INDEX
    Explanations

    technical alphanumeric patterns and strings, possibly related to computer programming or identification codes

    oai_token-act-pair · gpt-3.5-turbo

    character sequences or codes commonly associated with technical or software identifiers

    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
     closures
    -0.72
     scrut
    -0.69
     closure
    -0.67
     princ
    -0.64
     lamb
    -0.64
     barred
    -0.63
     prohibition
    -0.63
     compan
    -0.63
     spectator
    -0.62
     breat
    -0.61
    POSITIVE LOGITS
    dq
    1.03
    _-
    0.96
    AAAA
    0.94
    IU
    0.92
    rl
    0.90
    AAA
    0.88
    Lv
    0.87
    001
    0.85
    dn
    0.85
    OY
    0.85
    Activations Density 0.131%

    No Known Activations