© 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. 9-RES-JB
    11. 1889
    Prev
    Next
    INDEX
    Explanations

    mentions of legal procedures, actions, and conditions such as bail, plans, drive, not guilty plea, bond, and detention

    oai_token-act-pair · gpt-3.5-turbo

    references to driving and transport-related situations

    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
     unison
    -0.88
     ourselves
    -0.60
     Ranked
    -0.58
     epoch
    -0.56
     %%
    -0.56
     Sweep
    -0.56
     Subtle
    -0.55
     yourselves
    -0.54
     Splash
    -0.54
     Detected
    -0.53
    POSITIVE LOGITS
     himself
    0.92
     his
    0.83
     herself
    0.79
    His
    0.79
     hers
    0.72
     whereabouts
    0.71
     counselling
    0.69
    .�
    0.68
    his
    0.68
    VERTISEMENT
    0.65
    Activations Density 0.935%

    No Known Activations