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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 7520
    Prev
    Next
    INDEX
    Explanations

    mentions of physical violence, specifically beatings

    oai_token-act-pair · gpt-3.5-turbo

    words related to physical violence and assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isse
    -0.86
    oplan
    -0.74
     facult
    -0.74
    merce
    -0.69
     sender
    -0.68
    orrow
    -0.68
     mosqu
    -0.67
    Import
    -0.66
    udeau
    -0.65
    arij
    -0.65
    POSITIVE LOGITS
    down
    1.12
    downs
    0.90
    rice
    0.89
    beat
    0.88
    tle
    0.88
    boxing
    0.85
    up
    0.85
    ework
    0.83
    lass
    0.81
    masters
    0.80
    Activations Density 0.023%

    No Known Activations