© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 1034
    Prev
    Next
    INDEX
    Explanations

    data or measurements related to various subjects, such as rankings, chemical composition, mood, and habits

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to measurements and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clusive
    -0.73
    cott
    -0.69
    ibus
    -0.68
    ulo
    -0.66
    pired
    -0.66
    fox
    -0.65
    lyn
    -0.65
    nov
    -0.64
    isha
    -0.64
    thouse
    -0.63
    POSITIVE LOGITS
     suscept
    0.83
     preferences
    0.80
     differed
    0.80
     attitudes
    0.80
     probabilities
    0.79
     tendencies
    0.78
     stru
    0.75
     differently
    0.75
     habits
    0.75
     disposition
    0.74
    Activations Density 0.760%

    No Known Activations