Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5143
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to email promotions

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation and formatting in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iter
    -0.74
    Foot
    -0.68
    rely
    -0.67
    ensical
    -0.65
    orable
    -0.65
    olas
    -0.65
     comprom
    -0.65
    paces
    -0.65
    imus
    -0.62
    uder
    -0.62
    POSITIVE LOGITS
    ,,,,,,,,
    0.88
    ::::::::
    0.84
    ,,,,
    0.81
    ::::
    0.75
    taboola
    0.72
    tel
    0.72
    then
    0.71
    tra
    0.69
    ;;;;;;;;;;;;
    0.68
     Lad
    0.66
    Activations Density 0.030%

    No Known Activations