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. 9713
    Prev
    Next
    INDEX
    Explanations

    blood-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to blood and its various associations

    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
    awaru
    -0.89
    OPLE
    -0.78
    ECH
    -0.76
    IX
    -0.75
     VIDEOS
    -0.74
     Amend
    -0.73
    VICE
    -0.72
    ALS
    -0.70
    VERS
    -0.68
     Lank
    -0.68
    POSITIVE LOGITS
    thirst
    1.36
    bath
    1.22
    hound
    1.20
    stained
    1.16
    lust
    1.11
    shed
    1.01
     thirsty
    0.95
    wine
    0.92
     vessels
    0.92
     spilled
    0.89
    Activations Density 0.017%

    No Known Activations