© 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. 6-RES-JB
    11. 11874
    Prev
    Next
    INDEX
    Explanations

    words related to giving or offering something to someone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a" coupled with various actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nel
    -0.77
    ources
    -0.69
    ador
    -0.67
    ami
    -0.66
    agree
    -0.66
    inois
    -0.66
    anism
    -0.65
    ous
    -0.65
    atoon
    -0.63
     Transactions
    -0.61
    POSITIVE LOGITS
     chance
    1.12
     glimpse
    1.05
     lot
    0.95
     nickname
    0.88
     foothold
    0.87
     piece
    0.86
     distinctive
    0.84
     bunch
    0.84
     hearty
    0.84
     fresh
    0.84
    Activations Density 0.079%

    No Known Activations