© 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. 17206
    Prev
    Next
    INDEX
    Explanations

    phrases indicating multiple individuals along with negative or impactful events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals and their involvement in various incidents or events

    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
    Temperature
    -0.72
    Natural
    -0.67
    tnc
    -0.67
     Parables
    -0.66
    à¤
    -0.66
    ãĤ¦
    -0.66
    Leader
    -0.64
    osterone
    -0.62
    itiveness
    -0.61
    Order
    -0.61
    POSITIVE LOGITS
     apiece
    1.02
     accused
    0.97
     implicated
    0.94
     boarded
    0.93
     died
    0.82
     indicted
    0.81
     abducted
    0.80
     whom
    0.78
     parach
    0.78
     suspected
    0.77
    Activations Density 0.197%

    No Known Activations