© 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. 1551
    Prev
    Next
    INDEX
    Explanations

    examples of verbs related to changing states, such as melting or boiling

    oai_token-act-pair · gpt-3.5-turbo

    terms related to melting and physical changes in materials

    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
    76561
    -0.77
    é¾įå
    -0.73
    ourt
    -0.70
     è£ıç
    -0.70
     deleg
    -0.65
    onnaissance
    -0.65
    phies
    -0.62
    ocations
    -0.61
    ZI
    -0.60
    zan
    -0.60
    POSITIVE LOGITS
     smoothly
    1.08
     explos
    1.07
     spontaneously
    1.06
     violently
    1.01
     horribly
    1.00
     uncontroll
    1.00
     mysteriously
    0.95
     faster
    0.94
     nicely
    0.93
     into
    0.91
    Activations Density 0.274%

    No Known Activations