© 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. 14040
    Prev
    Next
    INDEX
    Explanations

    proper nouns and phrases related to listings or registrations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to items being formally documented or recognized in lists or registries

    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
    icz
    -0.74
    qua
    -0.70
    wards
    -0.59
    assi
    -0.58
     inflicted
    -0.57
     loop
    -0.57
    ework
    -0.57
    urai
    -0.56
    outer
    -0.56
    usterity
    -0.55
    POSITIVE LOGITS
     alphabet
    0.97
     trademarks
    0.83
    entin
    0.81
     tradem
    0.80
     Seller
    0.76
    daq
    0.76
    enance
    0.73
     prominently
    0.69
     listings
    0.69
     below
    0.69
    Activations Density 0.040%

    No Known Activations