Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13924
    Prev
    Next
    INDEX
    Explanations

    names or references to the name "Hal"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nomine
    -0.74
    ãģį
    -0.71
    holders
    -0.68
    ãģķ
    -0.67
    hips
    -0.63
    URES
    -0.63
     CLS
    -0.62
    holding
    -0.61
    wrapper
    -0.60
    CRIP
    -0.60
    POSITIVE LOGITS
    ftime
    1.07
    ifax
    1.04
    ibur
    1.01
    iday
    0.97
    ogen
    0.86
    ocaust
    0.84
    monds
    0.83
    enn
    0.83
     9000
    0.81
    endar
    0.79
    Activations Density 0.022%

    No Known Activations