© 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. 3-RES-JB
    11. 13534
    Prev
    Next
    INDEX
    Explanations

    names referencing specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and terms associated with individuals or companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icipated
    -0.90
    ware
    -0.80
    clinton
    -0.80
    osate
    -0.77
    ORED
    -0.76
    enegger
    -0.75
    stood
    -0.74
    ĺħ
    -0.73
    oral
    -0.71
    olid
    -0.71
    POSITIVE LOGITS
    ijn
    0.94
    nder
    0.87
     Kru
    0.85
    gment
    0.82
    gments
    0.81
    sts
    0.80
    gement
    0.79
    pid
    0.78
    ggles
    0.77
     Klux
    0.76
    Activations Density 0.006%

    No Known Activations