© 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. 7-RES-JB
    11. 1624
    Prev
    Next
    INDEX
    Explanations

    phrases related to the latest updates or releases in a series or sequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the latest developments or trends in various contexts

    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
     fork
    -0.67
     vulner
    -0.63
     swayed
    -0.61
    WHERE
    -0.61
     lapt
    -0.57
     aloud
    -0.56
     aided
    -0.56
     perched
    -0.56
     guarant
    -0.55
     entertained
    -0.55
    POSITIVE LOGITS
    organic
    0.98
    offensive
    0.97
    authent
    0.95
    escap
    0.93
    patient
    0.92
    roads
    0.86
    clusions
    0.84
    arg
    0.84
    verts
    0.81
    herent
    0.76
    Activations Density 0.062%

    No Known Activations