© 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. 11109
    Prev
    Next
    INDEX
    Explanations

    names related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and teams

    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
     tremend
    -0.88
     conclud
    -0.80
    ©¶æ
    -0.79
    Þ
    -0.78
     Operation
    -0.77
     exting
    -0.75
     Orn
    -0.74
     acknow
    -0.74
     Paran
    -0.74
     comr
    -0.73
    POSITIVE LOGITS
    eret
    0.86
    iggs
    0.85
    inson
    0.85
    inho
    0.84
    essel
    0.84
    iesta
    0.79
    ijah
    0.77
    oise
    0.77
    aldi
    0.76
    achev
    0.75
    Activations Density 0.171%

    No Known Activations