© 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. 8-RES-JB
    11. 9859
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future intentions or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to future intentions or arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.77
    mint
    -0.76
    Cause
    -0.76
    INTON
    -0.69
     Temper
    -0.69
     Stain
    -0.68
    Interstitial
    -0.68
    enged
    -0.66
    rency
    -0.66
    iencies
    -0.64
    POSITIVE LOGITS
     obs
    0.90
    etting
    0.86
    emaker
    0.80
    isphere
    0.79
    etary
    0.79
     Parenthood
    0.78
     ahead
    0.75
    escape
    0.75
     plans
    0.74
     2030
    0.72
    Activations Density 0.049%

    No Known Activations