© 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. 18698
    Prev
    Next
    INDEX
    Explanations

    terms related to technological advancements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a significant amount or degree of something

    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
     Polo
    -0.75
     detachment
    -0.69
     Samp
    -0.67
     Suit
    -0.66
     Lock
    -0.65
     juggling
    -0.64
     Dice
    -0.64
    igon
    -0.64
     Compass
    -0.63
     composition
    -0.62
    POSITIVE LOGITS
    needed
    1.64
    anticipated
    1.55
    awaited
    1.42
    request
    1.27
    hyp
    1.26
    mal
    1.23
    respected
    1.14
    talk
    1.14
    crit
    1.14
    disc
    1.12
    Activations Density 0.050%

    No Known Activations