© 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. 2798
    Prev
    Next
    INDEX
    Explanations

    numeric ranges

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and ranges

    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
    utenberg
    -0.69
     Flavoring
    -0.68
    ota
    -0.67
    park
    -0.67
    awar
    -0.65
     Parish
    -0.65
    aceous
    -0.64
    Ĥª
    -0.62
     Alic
    -0.62
     Parker
    -0.60
    POSITIVE LOGITS
    31
    1.26
    33
    1.15
    34
    1.14
    32
    1.13
    35
    1.12
     31
    1.12
    30
    1.11
    36
    1.09
    37
    1.08
    38
    1.07
    Activations Density 0.077%

    No Known Activations