© 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. 11-RES-JB
    11. 9162
    Prev
    Next
    INDEX
    Explanations

    the letter "s" occurring either as a possessive marker or as part of a contraction

    oai_token-act-pair · gpt-3.5-turbo

    the word "there's" and its variations, indicating a focus on existential statements or introductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rounds
    -0.60
    roit
    -0.57
     stroke
    -0.57
     Continental
    -0.53
     Industries
    -0.53
     Economy
    -0.53
     WARN
    -0.52
     Observ
    -0.51
     oversaw
    -0.51
     Compared
    -0.51
    POSITIVE LOGITS
     plenty
    1.03
     nothing
    0.98
    been
    0.98
    omething
    0.93
     been
    0.92
    nothing
    0.88
    something
    0.86
    always
    0.84
     lots
    0.83
     something
    0.83
    Activations Density 0.063%

    No Known Activations