© 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. 2-RES-JB
    11. 8414
    Prev
    Next
    INDEX
    Explanations

    phrases related to high speed and urgency

    oai_token-act-pair · gpt-3.5-turbo

    references to speeding and urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ternity
    -0.82
    sym
    -0.74
    uyomi
    -0.73
    lymp
    -0.73
    rists
    -0.72
    choes
    -0.70
    rum
    -0.68
    ihar
    -0.67
    olith
    -0.67
    oral
    -0.66
    POSITIVE LOGITS
     speeding
    1.17
     speeds
    0.85
     sped
    0.83
     acceler
    0.80
     speed
    0.77
    wagon
    0.77
    EED
    0.76
     cooker
    0.74
     slows
    0.73
    peed
    0.72
    Activations Density 0.009%

    No Known Activations