© 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. 4-RES-JB
    11. 16714
    Prev
    Next
    INDEX
    Explanations

    the number 75

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the number 75

    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
    yang
    -0.82
     GOODMAN
    -0.78
    eering
    -0.77
    hran
    -0.75
    çīĪ
    -0.74
    gments
    -0.72
    ezvous
    -0.71
    gie
    -0.68
    chid
    -0.68
     sneaky
    -0.67
    POSITIVE LOGITS
     ILCS
    1.27
    ength
    0.96
    75
    0.90
    80
    0.85
    680
    0.84
    ULT
    0.82
    %:
    0.80
    475
    0.79
    875
    0.79
    pmwiki
    0.79
    Activations Density 0.022%

    No Known Activations