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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16472
    Prev
    Next
    INDEX
    Explanations

    mentions of age

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comp
    -0.66
     summ
    -0.64
     artic
    -0.63
     tant
    -0.62
     condu
    -0.62
     conspic
    -0.62
     coupled
    -0.61
     Scient
    -0.61
     spir
    -0.60
     communication
    -0.60
    POSITIVE LOGITS
    old
    4.39
    olds
    3.26
    OLD
    2.60
    older
    2.56
    olding
    2.27
    olded
    1.98
    Old
    1.92
    ould
    1.65
     old
    1.51
     olds
    1.37
    Activations Density 0.033%

    No Known Activations