© 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. 3142
    Prev
    Next
    INDEX
    Explanations

    four-digit numbers

    oai_token-act-pair · gpt-3.5-turbo
    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
    hire
    -0.90
    nd
    -0.81
    ouf
    -0.79
    lain
    -0.76
    roxy
    -0.75
    nda
    -0.74
    rup
    -0.71
    arij
    -0.70
    ritz
    -0.70
    dep
    -0.68
    POSITIVE LOGITS
    ized
    0.89
     digits
    0.84
    igr
    0.83
    ised
    0.81
    ographic
    0.80
    oded
    0.79
    itized
    0.79
    ization
    0.77
    eteen
    0.76
    umeric
    0.75
    Activations Density 0.027%

    No Known Activations