© 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. 9-RES-JB
    11. 15392
    Prev
    Next
    INDEX
    Explanations

    names

    oai_token-act-pair · gpt-3.5-turbo

    specific single-letter and multi-letter abbreviations or initials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RELE
    -0.71
    é¾įå¥ij士
    -0.71
     Dire
    -0.70
     UP
    -0.67
     MH
    -0.67
     RELEASE
    -0.66
    ãĤ°
    -0.63
     FORM
    -0.63
     Sigma
    -0.63
     Bom
    -0.62
    POSITIVE LOGITS
    immer
    1.21
    abs
    1.11
    orks
    1.10
    arma
    1.05
    ork
    1.03
    oker
    1.02
    arg
    1.00
    ogg
    0.99
    aps
    0.98
    ospital
    0.98
    Activations Density 0.104%

    No Known Activations