© 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. 0-RES-JB
    11. 13255
    Prev
    Next
    INDEX
    Explanations

    tokens or chunks related to a specific event or theme, such as "ev"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "ev" in various contexts or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Postal
    -0.67
     geared
    -0.67
     pillar
    -0.63
     designated
    -0.63
     rim
    -0.62
     sty
    -0.61
     rings
    -0.61
     framed
    -0.60
     massage
    -0.60
     prescription
    -0.60
    POSITIVE LOGITS
    ev
    4.66
    eva
    2.81
    EV
    2.08
    Ev
    1.88
    iev
    1.60
    evil
    1.49
     Ev
    1.43
    eb
    1.38
    ez
    1.38
    eve
    1.31
    Activations Density 0.011%

    No Known Activations