© 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. 10-RES-JB
    11. 16398
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future actions or events

    oai_token-act-pair · gpt-3.5-turbo

    future predictions or assertions about events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sending
    -0.59
     lett
    -0.59
     Doing
    -0.58
     delusions
    -0.56
     Tycoon
    -0.55
    doing
    -0.55
     seiz
    -0.55
     Viz
    -0.53
     projecting
    -0.52
    BuyableInstoreAndOnline
    -0.52
    POSITIVE LOGITS
     be
    1.00
     arise
    0.86
     exist
    0.82
     always
    0.82
    arcity
    0.80
    always
    0.78
    abouts
    0.75
     inevitably
    0.75
     BE
    0.72
    upon
    0.72
    Activations Density 0.042%

    No Known Activations