© 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. 16056
    Prev
    Next
    INDEX
    Explanations

    phrases about looking up to someone or something as a mentor or role model

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the action of "looking up."

    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
    kefeller
    -0.66
    Cu
    -0.63
    tering
    -0.63
     Cuomo
    -0.59
     Gupta
    -0.59
     Guan
    -0.58
    eer
    -0.58
    Anth
    -0.58
     Nation
    -0.57
    pload
    -0.57
    POSITIVE LOGITS
     acron
    0.71
    enance
    0.68
     favorably
    0.65
    grading
    0.65
    minster
    0.64
    raised
    0.64
    graded
    0.64
    stals
    0.63
    nces
    0.62
    river
    0.62
    Activations Density 0.030%

    No Known Activations