© 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. 17415
    Prev
    Next
    INDEX
    Explanations

    locations or addresses in the text

    oai_token-act-pair · gpt-3.5-turbo

    specific locations or addresses

    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
    Italy
    -0.88
    HTTP
    -0.82
    TPP
    -0.82
    Pakistan
    -0.81
    AFP
    -0.80
    zbollah
    -0.79
    Iran
    -0.76
    Syria
    -0.75
    METHOD
    -0.75
    Iraq
    -0.75
    POSITIVE LOGITS
     Meadow
    1.07
     Pleasant
    1.06
     Willow
    1.04
     Sweet
    1.01
     Deer
    0.99
     Cedar
    0.99
     Blossom
    0.98
     Maple
    0.98
     Birch
    0.97
     Speedway
    0.97
    Activations Density 0.232%

    No Known Activations