© 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. 17049
    Prev
    Next
    INDEX
    Explanations

    words related to advantages and disadvantages

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate various forms of excess or downsides

    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
    ¾
    -0.68
     floor
    -0.64
    Effective
    -0.64
    members
    -0.64
    YC
    -0.63
     VID
    -0.63
    IFE
    -0.62
    asus
    -0.62
    RFC
    -0.62
    LET
    -0.61
    POSITIVE LOGITS
    ettings
    0.97
    pring
    0.97
    uits
    0.94
     abound
    0.93
    ensical
    0.93
    hooting
    0.92
    hift
    0.92
    eries
    0.92
    hip
    0.89
     thereof
    0.89
    Activations Density 0.113%

    No Known Activations