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. 9-RES-JB
    6. 11791
    Prev
    Next
    INDEX
    Explanations

    legal or criminal charges related to violent or harmful actions against others

    oai_token-act-pair · gpt-3.5-turbo

    legal charges related to violent crimes and assaults

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.77
     spac
    -0.68
    ROM
    -0.68
    lopp
    -0.66
     shin
    -0.65
    opa
    -0.65
    isse
    -0.63
    SAM
    -0.63
    verse
    -0.62
    paren
    -0.61
    POSITIVE LOGITS
     manslaughter
    1.21
     offences
    1.05
     aggravated
    1.01
     punishable
    0.92
     felony
    0.90
     pursuant
    0.90
     charges
    0.90
     burglary
    0.89
     stemming
    0.88
     misdemeanor
    0.87
    Activations Density 0.156%

    No Known Activations