© 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. 11-RES-JB
    11. 3303
    Prev
    Next
    INDEX
    Explanations

    Prepositions indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    numerical rankings and positional data in a list context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.65
     exerted
    -0.61
    ivities
    -0.61
    oubted
    -0.60
     ampl
    -0.60
    oyle
    -0.60
    ighters
    -0.59
    ressive
    -0.59
    ÃĽ
    -0.58
    ĸļ
    -0.57
    POSITIVE LOGITS
     ninth
    1.45
     seventh
    1.44
     sixth
    1.42
     eighth
    1.41
     fifth
    1.34
     fourth
    1.34
     tenth
    1.19
     third
    1.19
     second
    1.11
     Nos
    1.10
    Activations Density 0.225%

    No Known Activations