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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14838
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Hol" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Hol" in various contexts

    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
    avorite
    -0.74
    REE
    -0.74
     Abyssal
    -0.71
    URI
    -0.71
    aeda
    -0.68
    kick
    -0.68
    å°Ĩ
    -0.67
    çĶ°
    -0.67
    omething
    -0.66
    EED
    -0.65
    POSITIVE LOGITS
    iday
    1.29
    idays
    1.28
    ocaust
    1.17
    mberg
    0.98
    brook
    0.95
    tro
    0.95
    inar
    0.93
    ocene
    0.91
     Hol
    0.90
    comb
    0.86
    Activations Density 0.008%

    No Known Activations