Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2291
    Prev
    Next
    INDEX
    Explanations

    numerical values preceded by specific terms

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to quantities and measures

    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
    EStreamFrame
    -0.69
     perspect
    -0.65
    PUT
    -0.59
     pastoral
    -0.58
    Frameworks
    -0.56
     welf
    -0.55
     Patri
    -0.52
    Products
    -0.52
    ¬¼
    -0.51
     pudding
    -0.51
    POSITIVE LOGITS
     22
    1.43
     14
    1.42
     33
    1.42
     15
    1.41
     34
    1.41
     32
    1.40
     13
    1.40
     23
    1.40
     16
    1.39
     17
    1.39
    Activations Density 0.331%

    No Known Activations