© 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. 8-RES-JB
    11. 20098
    Prev
    Next
    INDEX
    Explanations

    proper nouns, likely related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically personal names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ħ¢
    -0.67
    taboola
    -0.67
    OWER
    -0.65
     presumptive
    -0.65
    ¥µ
    -0.64
     undis
    -0.64
     Benghazi
    -0.64
    exempt
    -0.62
     totality
    -0.62
     Communists
    -0.60
    POSITIVE LOGITS
     Barker
    1.04
     Hansen
    1.00
     Roberts
    0.92
     Becker
    0.88
     Owen
    0.87
     Walsh
    0.86
     Wilde
    0.86
     Nichols
    0.85
     McInt
    0.84
    eric
    0.84
    Activations Density 0.302%

    No Known Activations