© 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. 21834
    Prev
    Next
    INDEX
    Explanations

    names of organizations followed by the word 'Action'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Action" related to various organizations and initiatives

    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
    artifacts
    -0.81
    hiba
    -0.73
    conservancy
    -0.72
    gins
    -0.69
    gling
    -0.68
    lease
    -0.66
    agar
    -0.66
    yth
    -0.66
     abundant
    -0.64
    ebin
    -0.63
    POSITIVE LOGITS
     Replay
    0.86
    tec
    0.80
    group
    0.70
    ual
    0.69
     Surge
    0.67
    ivism
    0.65
     Agency
    0.64
    ivated
    0.64
    ional
    0.64
     Bund
    0.64
    Activations Density 0.023%

    No Known Activations