© 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. 1-RES-JB
    11. 16384
    Prev
    Next
    INDEX
    Explanations

    mentions of political rallies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.91
    missions
    -0.73
    estinal
    -0.70
    ãģ¦
    -0.66
    chie
    -0.66
    ilk
    -0.65
    ricular
    -0.65
    Wan
    -0.64
    olly
    -0.64
     captcha
    -0.63
    POSITIVE LOGITS
     rally
    1.26
     rallies
    1.09
     Rally
    1.08
     rallying
    0.84
    eers
    0.83
    halla
    0.80
    eering
    0.78
    steen
    0.77
     chant
    0.77
    PsyNetMessage
    0.76
    Activations Density 0.014%

    No Known Activations