© 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. 4183
    Prev
    Next
    INDEX
    Explanations

    references to Senate Bills, specifically SB 9 and SB 8

    oai_token-act-pair · gpt-3.5-turbo

    references to specific pieces of legislation or bills

    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
    omorphic
    -0.78
     Dying
    -0.67
    Cause
    -0.65
    eers
    -0.63
    cule
    -0.63
     Hiroshima
    -0.62
    ghan
    -0.62
    rer
    -0.61
     indifference
    -0.60
    severe
    -0.60
    POSITIVE LOGITS
    aneers
    0.84
    ram
    0.83
    SB
    0.81
    arge
    0.80
    OTT
    0.80
    iff
    0.80
    UX
    0.79
    rams
    0.79
    undle
    0.77
    ORTS
    0.76
    Activations Density 0.017%

    No Known Activations