© 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. 7-RES-JB
    11. 18075
    Prev
    Next
    INDEX
    Explanations

    ages or descriptions related to specific ages (e.g., 36, 65)

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with ages

    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
    parency
    -0.65
     constitu
    -0.63
     stabilization
    -0.62
     prompt
    -0.61
     balcon
    -0.60
    ģ«
    -0.60
    itivity
    -0.60
     supplemental
    -0.59
     selection
    -0.59
    portion
    -0.58
    POSITIVE LOGITS
    %,
    0.84
    yo
    0.84
    %-
    0.76
    Jun
    0.72
    ½
    0.71
    pc
    0.70
     eldest
    0.69
    uncle
    0.68
     Rue
    0.68
    quartered
    0.67
    Activations Density 0.060%

    No Known Activations