© 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. 9909
    Prev
    Next
    INDEX
    Explanations

    terms related to progressing or improving something further

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating improvement or enhancement

    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
     skipping
    -0.67
    Reviewer
    -0.66
     Going
    -0.64
     LOT
    -0.64
     Tsukuyomi
    -0.64
     happening
    -0.64
     boarding
    -0.63
     quitting
    -0.63
     Walking
    -0.63
     sitting
    -0.63
    POSITIVE LOGITS
     differentiate
    1.25
     enhance
    1.23
     regulate
    1.19
     stimulate
    1.18
     integrate
    1.17
     complicate
    1.16
     define
    1.15
     promote
    1.15
     characterize
    1.14
     resemble
    1.12
    Activations Density 0.097%

    No Known Activations