© 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. 9-RES-JB
    11. 20828
    Prev
    Next
    INDEX
    Explanations

    phrases where the speaker expresses certainty or strong belief towards a statement

    oai_token-act-pair · gpt-3.5-turbo

    statements of agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    works
    -0.57
    NF
    -0.55
    pace
    -0.54
     RIS
    -0.54
     curve
    -0.54
     collision
    -0.53
     pitches
    -0.53
     resemblance
    -0.52
    dust
    -0.52
     Gaw
    -0.52
    POSITIVE LOGITS
    bered
    1.19
    oths
    1.17
    apy
    1.08
    othes
    1.00
    oner
    1.00
    othe
    0.96
    iled
    0.92
    zin
    0.86
    arer
    0.84
    iling
    0.84
    Activations Density 0.069%

    No Known Activations