© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 19393
    Prev
    Next
    INDEX
    Explanations

    comparisons mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    comparative statements or statistics related to political approval and public opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.86
    rup
    -0.66
    oslav
    -0.63
     proble
    -0.63
    NetMessage
    -0.63
    onym
    -0.62
    mop
    -0.62
    irie
    -0.62
     manufact
    -0.61
     è£ıè
    -0.59
    POSITIVE LOGITS
     compared
    1.08
     Including
    1.01
     whereas
    0.99
     according
    0.99
     including
    0.97
    excluding
    0.95
     excluding
    0.94
    according
    0.92
     totaling
    0.90
     implying
    0.87
    Activations Density 0.305%

    No Known Activations