© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 6965
    Prev
    Next
    INDEX
    Explanations

    various crime-related words and actions, including illegal activities, legal consequences, and criminal investigations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conflict and legal situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antage
    -0.67
    ¿½
    -0.66
    ãĥij
    -0.65
    plete
    -0.64
    iven
    -0.63
    aic
    -0.63
    sequ
    -0.63
    icating
    -0.62
    Sit
    -0.62
    EEK
    -0.61
    POSITIVE LOGITS
     knows
    1.37
     believes
    1.29
     thinks
    1.29
     testified
    1.26
     remembers
    1.26
     complains
    1.24
     admits
    1.22
     receives
    1.21
     died
    1.21
     dies
    1.19
    Activations Density 0.400%

    No Known Activations