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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 3065
    Prev
    Next
    INDEX
    Explanations

    names of French- or Spanish-speaking restaurants

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or places, particularly "Gir" and "Sud"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ension
    -0.83
    yright
    -0.80
    ilot
    -0.79
    enses
    -0.71
    rodu
    -0.70
    ewater
    -0.70
    ograph
    -0.69
    iser
    -0.68
     Lann
    -0.67
    itored
    -0.66
    POSITIVE LOGITS
    rand
    0.77
    gence
    0.75
    dale
    0.71
    go
    0.70
    geon
    0.70
    bats
    0.69
    tags
    0.69
    leys
    0.67
    saf
    0.67
    gue
    0.66
    Activations Density 0.048%

    No Known Activations