© 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. 2-RES-JB
    11. 1441
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name, possibly a person's name "Hin"

    oai_token-act-pair · gpt-3.5-turbo

    names or terms related to people, particularly those with the suffix 'hin'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.64
     srf
    -0.63
     Seym
    -0.62
    urally
    -0.61
    Reference
    -0.61
    lished
    -0.60
    Loading
    -0.60
     Anarchy
    -0.60
    multipl
    -0.60
     manifest
    -0.59
    POSITIVE LOGITS
    osaurs
    1.05
    eman
    1.04
    emen
    0.98
    agar
    0.97
    ryu
    0.94
    ned
    0.93
    ners
    0.90
    hin
    0.89
    ewater
    0.89
    erella
    0.88
    Activations Density 0.012%

    No Known Activations