© 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. 0-RES-JB
    11. 22198
    Prev
    Next
    INDEX
    Explanations

    words related to electronic devices or technology like "TV" or "Linux"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of technology and media content, especially related to television and Android

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÂŃ
    -0.91
    —
    -0.81
     Gamble
    -0.81
     Singer
    -0.80
     Belt
    -0.78
     Dow
    -0.78
     Spur
    -0.77
     Slate
    -0.77
     Baker
    -0.76
     Pitch
    -0.75
    POSITIVE LOGITS
     dont
    2.06
     doesnt
    1.97
     didnt
    1.94
     english
    1.83
     americ
    1.78
     linux
    1.72
     js
    1.72
     google
    1.71
     cs
    1.70
     tv
    1.69
    Activations Density 0.100%

    No Known Activations