© 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. 1887
    Prev
    Next
    INDEX
    Explanations

    hyperlinks

    oai_token-act-pair · gpt-3.5-turbo

    URLs and links to online resources

    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
     Pigs
    -0.78
     Lowell
    -0.76
     Ratio
    -0.72
     Wonderland
    -0.71
     Lep
    -0.71
     Mayo
    -0.70
     Decay
    -0.69
     Camer
    -0.67
     Ago
    -0.65
     Baxter
    -0.65
    POSITIVE LOGITS
    github
    1.76
    twitter
    1.61
    www
    1.35
    medium
    1.32
    docs
    1.30
    doi
    1.20
    youtu
    1.15
    mega
    1.10
    natureconservancy
    1.09
    encrypted
    1.08
    Activations Density 0.020%

    No Known Activations