© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 6356
    Prev
    Next
    INDEX
    Explanations

    the word "no" followed by other words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating absence or lack of something

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

    No Comments

    Negative Logits
    RAFT
    -0.78
    assies
    -0.75
    rex
    -0.66
    lycer
    -0.66
    gnu
    -0.66
    adobe
    -0.65
    iership
    -0.65
    dor
    -0.64
    aven
    -0.63
    ommod
    -0.62
    POSITIVE LOGITS
    xious
    1.25
     longer
    1.07
     doubt
    1.00
     matter
    0.96
    except
    0.95
    oses
    0.90
     indication
    0.87
     conceivable
    0.83
    oooooooo
    0.83
     guarantee
    0.83
    Activations Density 0.093%

    No Known Activations