© 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. 2782
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, requirements, customs, and norms

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to rules and protocols

    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
    gdala
    -0.64
     Lash
    -0.63
    ographics
    -0.62
    ravings
    -0.62
    letters
    -0.60
    acement
    -0.58
     nutshell
    -0.57
    resa
    -0.57
    iken
    -0.56
    plates
    -0.54
    POSITIVE LOGITS
     considering
    0.99
     incidentally
    0.94
     anyway
    0.83
     since
    0.83
    !).
    0.81
    )}
    0.81
     anecd
    0.80
     nowadays
    0.80
    ).
    0.79
     when
    0.76
    Activations Density 0.364%

    No Known Activations