© 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. 11627
    Prev
    Next
    INDEX
    Explanations

    action sentences that involve either hypothetical or speculative scenarios

    oai_token-act-pair · gpt-3.5-turbo

    speculative phrases or statements that imply uncertainty or possibility

    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
    athing
    -0.76
    bread
    -0.71
    ohan
    -0.69
    raint
    -0.69
    rake
    -0.67
    Virgin
    -0.66
    ussions
    -0.65
    ride
    -0.65
    Driver
    -0.64
    verse
    -0.63
    POSITIVE LOGITS
     misunder
    0.87
     alternatively
    0.85
     incent
    0.76
     unintentional
    0.72
    idon
    0.70
     summarized
    0.70
    ©¶æ
    0.70
     argued
    0.69
     intu
    0.67
     exacerbated
    0.65
    Activations Density 0.168%

    No Known Activations