© 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. 2411
    Prev
    Next
    INDEX
    Explanations

    arrays or list-like structures

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data or statistics

    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
    ãĤ§
    -0.65
    ĨĴ
    -0.60
    uyomi
    -0.57
    ãĥĩãĤ£
    -0.56
    ppings
    -0.54
    ãĤ·ãĥ£
    -0.54
    ãĥ´ãĤ¡
    -0.50
    ope
    -0.50
    alty
    -0.50
    ãĥĥ
    -0.49
    POSITIVE LOGITS
     in
    1.41
    in
    1.21
     IN
    1.06
    In
    1.04
     In
    1.00
     therein
    0.94
    inen
    0.88
     elsewhere
    0.85
     inside
    0.80
    IN
    0.80
    Activations Density 0.480%

    No Known Activations