© 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. 2-RES-JB
    11. 17352
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific entity named "Hol"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Hol" or its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REE
    -0.72
    kick
    -0.67
    avorite
    -0.66
     nomine
    -0.66
    å°Ĩ
    -0.65
    aeda
    -0.64
    define
    -0.64
    URI
    -0.63
    Rated
    -0.63
     unauthorized
    -0.62
    POSITIVE LOGITS
    iday
    1.34
    idays
    1.32
    ocaust
    1.20
     Hol
    1.01
    ocene
    0.93
    mberg
    0.93
    oho
    0.91
    tro
    0.85
    brook
    0.85
    seys
    0.84
    Activations Density 0.004%

    No Known Activations