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. 10095
    Prev
    Next
    INDEX
    Explanations

    various types or categories of things mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to various categories or classifications

    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
    ITED
    -0.70
    NING
    -0.68
     Mald
    -0.61
    IRO
    -0.61
    ometown
    -0.61
    ITNESS
    -0.60
     Morning
    -0.60
     Kenya
    -0.59
     Rio
    -0.59
     Hus
    -0.58
    POSITIVE LOGITS
    etter
    1.47
    etting
    1.46
    faces
    1.07
    face
    0.91
    classes
    0.88
    isms
    0.87
    ahead
    0.83
    otypes
    0.82
    chool
    0.81
    linger
    0.80
    Activations Density 0.017%

    No Known Activations