© 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. 23246
    Prev
    Next
    INDEX
    Explanations

    statements or questions starting with 'a' followed by a verb and object

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" and related phrases signaling a question or issue

    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
    otte
    -0.77
    peed
    -0.74
    rates
    -0.74
    anism
    -0.73
    acid
    -0.73
    tm
    -0.72
    eligible
    -0.71
    votes
    -0.70
     Attend
    -0.70
    agents
    -0.69
    POSITIVE LOGITS
     fascinating
    1.22
     plethora
    1.20
     lot
    1.20
     tremendous
    1.08
     profound
    1.08
     startling
    1.07
     multitude
    1.07
     deeper
    1.07
     refreshing
    1.07
     considerable
    1.02
    Activations Density 0.286%

    No Known Activations