© 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. 20021
    Prev
    Next
    INDEX
    Explanations

    narrative sentences describing events or actions taking place

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be."

    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
    inav
    -0.77
     HAVE
    -0.70
     Previous
    -0.67
    omial
    -0.66
     Have
    -0.66
     Lines
    -0.65
     Compare
    -0.64
     Lack
    -0.64
     Statements
    -0.64
    occ
    -0.64
    POSITIVE LOGITS
     eventually
    1.33
     rewarded
    1.25
     able
    1.20
     unable
    1.19
     ultimately
    1.15
     subsequently
    1.12
     unsuccessful
    1.12
     reunited
    1.11
     promptly
    1.10
     finally
    1.08
    Activations Density 0.431%

    No Known Activations