© 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. 11-RES-JB
    11. 18713
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I’m going to" indicating intentions or future plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essa
    -0.58
     Flavoring
    -0.58
    ullah
    -0.58
    ament
    -0.56
    alys
    -0.56
    archives
    -0.55
    clips
    -0.55
    hold
    -0.54
    urus
    -0.53
    holding
    -0.53
    POSITIVE LOGITS
     to
    1.06
     overboard
    0.83
     nowhere
    0.80
     crazy
    0.80
     nuts
    0.75
     insane
    0.73
     ta
    0.72
     extinct
    0.71
     mad
    0.69
     HAM
    0.67
    Activations Density 0.051%

    No Known Activations