© 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. 24058
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology usage

    oai_token-act-pair · gpt-3.5-turbo

    repetitive usage of the word "the."

    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
    boxing
    -0.72
    mire
    -0.70
    odiac
    -0.68
    ohm
    -0.68
    ISTORY
    -0.65
    /
    -0.64
    ablishment
    -0.64
    ventus
    -0.64
    ufact
    -0.63
    Init
    -0.63
    POSITIVE LOGITS
     pseudonym
    1.19
     hashtag
    1.15
     phrase
    1.11
     restroom
    1.06
     same
    1.04
     term
    0.99
     excuse
    0.98
     pronoun
    0.96
     analogy
    0.96
     tactic
    0.95
    Activations Density 0.107%

    No Known Activations