© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 22559
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names of individuals being appointed or selected to lead various organizations or departments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lead" in various contexts related to leadership positions or roles

    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
    eon
    -0.66
    pton
    -0.65
    ramid
    -0.63
    Sov
    -0.63
    aves
    -0.61
    ascade
    -0.61
    cube
    -0.60
    phis
    -0.59
    orrow
    -0.59
    pmwiki
    -0.58
    POSITIVE LOGITS
    lead
    1.00
    ership
    0.99
    better
    0.91
    gers
    0.82
    leaders
    0.78
    boards
    0.75
     Leading
    0.74
    Lead
    0.73
     usher
    0.71
    gest
    0.71
    Activations Density 0.035%

    No Known Activations