© 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. 3118
    Prev
    Next
    INDEX
    Explanations

    names of individuals with the initial "P" followed by a number

    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
    æ©Ł
    -0.77
    æ©
    -0.69
     Gleaming
    -0.69
     GOODMAN
    -0.68
     hairs
    -0.67
     warr
    -0.67
    MpServer
    -0.66
     GEAR
    -0.64
     contrace
    -0.64
    ãĤĬ
    -0.64
    POSITIVE LOGITS
    ossible
    1.43
    ulse
    1.29
    redict
    1.27
    resents
    1.26
    olitan
    1.24
    ossession
    1.23
    ixels
    1.23
    ilot
    1.22
    overty
    1.19
    ivot
    1.18
    Activations Density 0.063%

    No Known Activations