© 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. 4-RES-JB
    11. 656
    Prev
    Next
    INDEX
    Explanations

    names, specifically focusing on the last part of the name

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of 'nose' references

    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
    icum
    -0.73
    ersen
    -0.73
    ertodd
    -0.72
    ufact
    -0.71
     ILCS
    -0.71
    rators
    -0.69
    agna
    -0.68
    cdn
    -0.67
    angible
    -0.67
    è¦ļéĨĴ
    -0.66
    POSITIVE LOGITS
    velt
    1.12
    cond
    1.07
    lihood
    1.01
    idon
    0.94
    lect
    0.94
    eker
    0.91
    ppe
    0.84
    OPLE
    0.82
    ppel
    0.81
    ptic
    0.79
    Activations Density 0.015%

    No Known Activations