© 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. 7-RES-JB
    11. 18843
    Prev
    Next
    INDEX
    Explanations

    words related to behavior and actions, particularly those related to misbehavior and good behavior

    oai_token-act-pair · gpt-3.5-turbo

    terms related to behavior, particularly in reference to individuals or groups

    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
    eous
    -0.79
    ographical
    -0.68
    smanship
    -0.67
     [+
    -0.67
    zai
    -0.67
    ographers
    -0.65
    ieth
    -0.63
    oan
    -0.60
     Snow
    -0.60
     pole
    -0.60
    POSITIVE LOGITS
    aviour
    1.42
    avior
    0.99
    reath
    0.87
    avin
    0.87
    avi
    0.84
    aving
    0.81
    ¡
    0.80
    rup
    0.80
    av
    0.79
    isance
    0.78
    Activations Density 0.059%

    No Known Activations