© 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. 9506
    Prev
    Next
    INDEX
    Explanations

    instances of words containing the stem "plut" that could be related to wealth, power, or political influence

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases associated with political structures or governance

    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
    ĸļ
    -0.82
     bartender
    -0.66
     reven
    -0.61
    PRES
    -0.60
     reckoning
    -0.59
     Clapper
    -0.57
    Quant
    -0.56
     Wraith
    -0.56
     pronounced
    -0.56
     KNOW
    -0.56
    POSITIVE LOGITS
    olini
    0.84
    aple
    0.82
    ions
    0.79
    emouth
    0.76
    asant
    0.76
    ibilities
    0.73
    encia
    0.73
    igham
    0.73
    irts
    0.72
    estine
    0.72
    Activations Density 0.075%

    No Known Activations