© 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. 4-RES-JB
    11. 15323
    Prev
    Next
    INDEX
    Explanations

    the string "Han" and related words

    oai_token-act-pair · gpt-3.5-turbo

    the name "Han" across various contexts

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

    No Comments

    Negative Logits
    anwhile
    -0.84
     destro
    -0.82
    utics
    -0.71
    URES
    -0.70
    Downloadha
    -0.70
    ktop
    -0.68
    okemon
    -0.68
    ODUCT
    -0.67
    atoon
    -0.67
    terday
    -0.67
    POSITIVE LOGITS
    auer
    0.97
    uman
    0.95
    ning
    0.91
    ifa
    0.89
    wei
    0.88
    lon
    0.87
     Solo
    0.87
    bang
    0.86
    wal
    0.82
    hart
    0.81
    Activations Density 0.008%

    No Known Activations