© 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. 18639
    Prev
    Next
    INDEX
    Explanations

    negatively connotated words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "unf," indicating negation or absence

    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
     gorilla
    -0.68
    ãĥ£
    -0.67
     gas
    -0.65
     partName
    -0.65
     buckle
    -0.65
     gear
    -0.65
     Dag
    -0.64
     Madness
    -0.64
     Kry
    -0.63
     simulations
    -0.62
    POSITIVE LOGITS
    riend
    1.62
    athom
    1.62
    ortunately
    1.50
    ortun
    1.49
    avour
    1.46
    aith
    1.41
    azed
    1.34
    rozen
    1.32
    ashion
    1.32
    avored
    1.31
    Activations Density 0.014%

    No Known Activations