© 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. 12858
    Prev
    Next
    INDEX
    Explanations

    information related to images, credits, and photo descriptions

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their contents

    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
     honors
    -0.76
     midterm
    -0.75
     honored
    -0.73
    luster
    -0.73
     canceled
    -0.70
     labor
    -0.68
     neocons
    -0.68
     enrollment
    -0.67
     favored
    -0.66
     Obama
    -0.66
    POSITIVE LOGITS
    NZ
    1.00
    BBC
    0.89
     BBC
    0.88
     ITV
    0.87
     fibre
    0.86
     IMAGES
    0.86
     Perth
    0.86
    Scotland
    0.85
     NZ
    0.81
     NRL
    0.80
    Activations Density 0.201%

    No Known Activations