© 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. 9309
    Prev
    Next
    INDEX
    Explanations

    phrases relating to comparisons or levels of quality

    oai_token-act-pair · gpt-3.5-turbo

    words related to the term "bespoke" in various contexts

    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
     antagonist
    -0.63
     inhib
    -0.58
     caps
    -0.57
    Ø©
    -0.56
     Yard
    -0.54
     suscept
    -0.54
     RBI
    -0.54
    ISON
    -0.54
     exit
    -0.53
     NS
    -0.53
    POSITIVE LOGITS
    poke
    1.40
    erker
    1.27
    pect
    1.22
    earch
    1.15
    iege
    1.14
    earchers
    1.09
    hing
    1.09
    peak
    1.05
    quite
    1.03
    coe
    1.01
    Activations Density 0.049%

    No Known Activations