© 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. 4-RES-JB
    11. 10984
    Prev
    Next
    INDEX
    Explanations

    ages, typically indicating an age at the start of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ages or numerical values related to age

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

    No Comments

    Negative Logits
     guid
    -0.84
    igham
    -0.70
     mislead
    -0.67
     Greenwald
    -0.66
    llor
    -0.65
     targeting
    -0.64
    agate
    -0.59
    reference
    -0.59
    olicy
    -0.59
     targeted
    -0.59
    POSITIVE LOGITS
    teen
    1.01
    teenth
    1.00
    ½
    0.95
    een
    0.95
    th
    0.87
     years
    0.85
    %,
    0.84
    %-
    0.83
     stitches
    0.82
    ciating
    0.82
    Activations Density 0.340%

    No Known Activations