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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3443
    Prev
    Next
    INDEX
    Explanations

    words related to blood, violence, or conflict

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to bloodshed or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.87
    OPLE
    -0.82
     Amend
    -0.79
    IX
    -0.78
     VIDEOS
    -0.76
    ALS
    -0.76
    ECH
    -0.75
     Lank
    -0.73
    VICE
    -0.72
    acle
    -0.70
    POSITIVE LOGITS
    thirst
    1.41
    bath
    1.28
    hound
    1.22
    stained
    1.22
    lust
    1.09
    shed
    1.05
     thirsty
    0.97
    wine
    0.94
     vessels
    0.94
    lines
    0.92
    Activations Density 0.023%

    No Known Activations