© 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. 20300
    Prev
    Next
    INDEX
    Explanations

    words related to predictions or expectations

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and future possibilities

    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
    DAQ
    -0.63
     festive
    -0.59
    ida
    -0.58
     dun
    -0.58
    Tips
    -0.57
     Completed
    -0.57
    ths
    -0.57
     contrasted
    -0.56
    LD
    -0.55
     Sporting
    -0.55
    POSITIVE LOGITS
     be
    1.20
     someday
    1.04
     eventually
    1.00
     inevitably
    0.87
     become
    0.87
    soon
    0.86
     unleash
    0.86
     achieve
    0.86
     succeed
    0.84
     arrive
    0.83
    Activations Density 0.261%

    No Known Activations