© 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. 10-RES-JB
    11. 9955
    Prev
    Next
    INDEX
    Explanations

    descriptions of individuals based on age

    oai_token-act-pair · gpt-3.5-turbo

    references to age, specifically using the term "old."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichick
    -0.97
    TIME
    -0.92
    rosis
    -0.88
    vernment
    -0.82
    icter
    -0.80
    SHIP
    -0.78
    acly
    -0.77
    entimes
    -0.77
    gone
    -0.77
    oldown
    -0.76
    POSITIVE LOGITS
     freshman
    1.06
     sophomore
    1.04
     student
    0.96
     boy
    0.90
     Frenchman
    0.90
     Nigerian
    0.89
     pupil
    0.88
     Mississ
    0.86
     graduate
    0.86
     girl
    0.86
    Activations Density 0.060%

    No Known Activations