© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 19751
    Prev
    Next
    INDEX
    Explanations

    words related to the fictional detective Sherlock Holmes

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Sherlock Holmes

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

    No Comments

    Negative Logits
    ital
    -0.82
    ribute
    -0.78
    ript
    -0.71
    racted
    -0.70
    inished
    -0.68
    å§
    -0.68
    resent
    -0.68
    abet
    -0.67
    healthy
    -0.67
    ribut
    -0.66
    POSITIVE LOGITS
     Holmes
    1.17
    iday
    0.85
    Lens
    0.82
     Hole
    0.73
    ville
    0.72
    BUR
    0.70
    combe
    0.70
     Manor
    0.70
     Weasley
    0.70
     Circus
    0.68
    Activations Density 0.009%

    No Known Activations