© 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. 6-RES-JB
    11. 14961
    Prev
    Next
    INDEX
    Explanations

    information related to incidents involving men, such as arrests, injuries, and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to male individuals in various contexts, especially in crime-related situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļ
    -0.96
    aeda
    -0.77
    æ©Ł
    -0.75
    inventoryQuantity
    -0.75
    tnc
    -0.72
    æĪ¦
    -0.71
     Grid
    -0.71
    âĶĢâĶĢâĶĢâĶĢ
    -0.71
     Machines
    -0.70
    éĹĺ
    -0.69
    POSITIVE LOGITS
    hunt
    1.14
    endez
    0.98
     who
    0.92
    ishly
    0.84
     WHO
    0.82
    ish
    0.82
     accused
    0.80
     whom
    0.78
     named
    0.77
     whose
    0.77
    Activations Density 0.113%

    No Known Activations