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. 11-RES-JB
    6. 20103
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal, cultural, and economic aspects

    oai_token-act-pair · gpt-3.5-turbo

    statements about conditions or situations that are commonly accepted or prevalent in various contexts

    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
     Adds
    -0.65
     Shape
    -0.63
     Sew
    -0.63
     Changes
    -0.62
    wake
    -0.62
    ERAL
    -0.61
     Lawn
    -0.60
    oning
    -0.60
    soType
    -0.59
    ividual
    -0.59
    POSITIVE LOGITS
     predominant
    1.00
     scarce
    0.98
     plentiful
    0.98
     concerned
    0.92
     paramount
    0.90
     routinely
    0.90
     commonplace
    0.89
     reckoned
    0.89
     pitted
    0.88
     indistinguishable
    0.88
    Activations Density 0.187%

    No Known Activations