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. 8-RES-JB
    6. 22907
    Prev
    Next
    INDEX
    Explanations

    words related to specific groups or categories, such as professions, demographics, or ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or categories of people and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrimmage
    -0.66
    ulative
    -0.59
     Held
    -0.59
    iasis
    -0.58
     0004
    -0.56
     Carbuncle
    -0.54
    rift
    -0.54
    oward
    -0.54
    umn
    -0.54
    ieves
    -0.53
    POSITIVE LOGITS
     itself
    1.16
     ones
    1.11
     themselves
    0.98
    )</
    0.89
    !).
    0.87
     thereof
    0.83
     himself
    0.83
     herself
    0.81
    ).[
    0.77
    ).
    0.76
    Activations Density 0.570%

    No Known Activations