© 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. 1687
    Prev
    Next
    INDEX
    Explanations

    words related to legal or political actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    action verbs that indicate support or endorsement

    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
    been
    -0.80
    yond
    -0.72
    é¾įå¥ij士
    -0.71
    coin
    -0.70
    isable
    -0.69
    wcsstore
    -0.67
    yet
    -0.65
    borne
    -0.65
    pic
    -0.64
    ():
    -0.63
    POSITIVE LOGITS
    hement
    0.77
     unanimously
    0.74
     unsuccessfully
    0.74
     him
    0.67
     nervously
    0.66
     enthusiastically
    0.66
     valiant
    0.66
     furiously
    0.64
     Wem
    0.63
     tremend
    0.63
    Activations Density 0.525%

    No Known Activations