© 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. 4-RES-JB
    11. 9306
    Prev
    Next
    INDEX
    Explanations

    numerical values in the format "45 #", where # is a high value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 45 in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hers
    -0.89
    raltar
    -0.88
    cles
    -0.85
    MSN
    -0.80
    nesday
    -0.78
    undai
    -0.76
    gebra
    -0.72
    ascus
    -0.72
    gewater
    -0.71
    bern
    -0.69
    POSITIVE LOGITS
    678
    0.92
     degrees
    0.82
     minutes
    0.82
    ances
    0.82
     degree
    0.80
    ACP
    0.80
    rpm
    0.80
    %-
    0.79
    fps
    0.76
     ILCS
    0.76
    Activations Density 0.029%

    No Known Activations