© 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. 7-RES-JB
    11. 20733
    Prev
    Next
    INDEX
    Explanations

    words containing the prefix "un-"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the prefix "un-" indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     briefs
    -0.78
    OPLE
    -0.77
    anwhile
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.74
    hetti
    -0.71
     Tut
    -0.70
     Away
    -0.68
     Dynamics
    -0.66
     MX
    -0.66
     Blitz
    -0.65
    POSITIVE LOGITS
    balanced
    1.29
    ruly
    1.23
    assuming
    1.20
    ifying
    1.16
    apolog
    1.14
    availability
    1.14
    organized
    1.13
    cles
    1.12
    classified
    1.10
    earned
    1.09
    Activations Density 0.028%

    No Known Activations