© 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. 9-RES-JB
    11. 1050
    Prev
    Next
    INDEX
    Explanations

    comparisons of different situations over time

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )].
    -0.76
    erous
    -0.73
    ilic
    -0.56
    Bit
    -0.55
     Poe
    -0.54
    )]
    -0.53
    wiki
    -0.53
     Centauri
    -0.53
     Appropri
    -0.53
     Khan
    -0.53
    POSITIVE LOGITS
     ever
    1.04
     usual
    0.91
    before
    0.85
    usual
    0.85
    ever
    0.83
     EVER
    0.82
     elsewhere
    0.82
     anywhere
    0.81
     Previously
    0.79
     before
    0.76
    Activations Density 0.163%

    No Known Activations