© 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. 7-RES-JB
    11. 1831
    Prev
    Next
    INDEX
    Explanations

    phrases related to looking up to someone as a mentor or role model

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "looked up" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redo
    -0.68
    BAT
    -0.66
    pload
    -0.66
     Antar
    -0.64
    avery
    -0.61
    Cu
    -0.60
    oly
    -0.59
    apo
    -0.59
    ues
    -0.58
    eers
    -0.58
    POSITIVE LOGITS
    river
    0.80
    WARD
    0.68
    requently
    0.64
    horn
    0.63
    regulation
    0.63
    enance
    0.61
    draft
    0.61
     aloud
    0.60
     favorably
    0.59
    minist
    0.59
    Activations Density 0.020%

    No Known Activations