© 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. 2-RES-JB
    11. 866
    Prev
    Next
    INDEX
    Explanations

    references to the past, particularly the word "ago."

    oai_token-act-pair · gpt-4-turbo

    mentions of time-related data, particularly references to specific or approximate periods in the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods in the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hma
    -0.72
     lineback
    -0.72
    aspx
    -0.72
    ingham
    -0.70
    hop
    -0.67
     hemor
    -0.65
     Hispan
    -0.62
    ingle
    -0.62
    ixtape
    -0.62
     chromosome
    -0.61
    POSITIVE LOGITS
     ago
    1.05
    opausal
    0.79
     sunset
    0.70
     Invalid
    0.66
    âĢİ
    0.65
    ename
    0.64
    arians
    0.63
    EMBER
    0.63
    èª
    0.62
     Ples
    0.61
    Activations Density 0.021%

    No Known Activations