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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11-RES-JB
    6. 4050
    Prev
    Next
    INDEX
    Explanations

    entities such as groups of people or individuals related to specific contexts or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of people, particularly in relation to their roles, positions, or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.62
    riors
    -0.58
    nant
    -0.57
    rette
    -0.57
    ctors
    -0.57
    ĭ
    -0.57
    alde
    -0.56
    osate
    -0.56
    ":"","
    -0.54
    Phys
    -0.53
    POSITIVE LOGITS
    '
    2.68
    ']
    2.22
    '.
    1.89
    '/
    1.89
    ')
    1.88
    ',
    1.87
    '-
    1.85
    '"
    1.83
    ';
    1.72
    '?
    1.63
    Activations Density 0.815%

    No Known Activations