© 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. 6334
    Prev
    Next
    INDEX
    Explanations

    positive or negative affirmations

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing the concepts of "everything" and "nothing."

    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
    egal
    -0.69
    clus
    -0.67
     anonymity
    -0.65
     lucrative
    -0.64
    iership
    -0.64
    akedown
    -0.63
    ocratic
    -0.62
     touring
    -0.60
     Rih
    -0.60
     priesthood
    -0.60
    POSITIVE LOGITS
    Else
    1.00
    nces
    0.96
    body
    0.91
     Else
    0.91
     Dreams
    0.91
     else
    0.86
     Comes
    0.79
     Begins
    0.76
     Matters
    0.73
     Changes
    0.72
    Activations Density 0.083%

    No Known Activations