© 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. 9-RES-JB
    11. 1058
    Prev
    Next
    INDEX
    Explanations

    action-oriented phrases or instructions mentioned in messages, like "send you three meaningful actions."

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to time or frequency, particularly in the context of regular actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    x
    -0.77
     Kinnikuman
    -0.77
    xon
    -0.75
    OX
    -0.74
    ||
    -0.74
    Ear
    -0.74
    AR
    -0.74
    ear
    -0.74
     Esper
    -0.74
    xb
    -0.74
    POSITIVE LOGITS
    conservancy
    0.86
    atorium
    0.78
     cult
    0.76
     Cult
    0.75
    conserv
    0.69
    UMP
    0.68
     Conserv
    0.68
    secut
    0.67
    uls
    0.67
     Tribune
    0.67
    Activations Density 0.389%

    No Known Activations