Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 2948
    Prev
    Next
    INDEX
    Explanations

    locations and names, especially those related to legal or medical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and individuals, particularly names

    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
    smoking
    -0.73
    aceous
    -0.71
    ILE
    -0.69
    =-=-=-=-=-=-=-=-
    -0.68
    TPP
    -0.68
    eger
    -0.67
    uality
    -0.66
    apers
    -0.65
    Japanese
    -0.64
    zza
    -0.64
    POSITIVE LOGITS
     Nass
    1.16
    daq
    1.03
    essor
    0.85
    mares
    0.81
    itud
    0.78
     Tanz
    0.75
    aran
    0.74
    itude
    0.72
    arus
    0.71
     horizont
    0.71
    Activations Density 0.005%

    No Known Activations