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. 7-RES-JB
    6. 2334
    Prev
    Next
    INDEX
    Explanations

    descriptions of events and activities

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of live events and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atron
    -0.79
     comprom
    -0.70
     defic
    -0.69
    chnology
    -0.65
    Process
    -0.65
    kernel
    -0.65
    ©¶æ¥µ
    -0.63
    _.
    -0.63
    artz
    -0.62
    Weak
    -0.62
    POSITIVE LOGITS
     festive
    0.98
     festivals
    0.95
     festival
    0.95
     scenic
    0.93
     concerts
    0.84
     chore
    0.83
     Carnival
    0.83
     festivities
    0.83
     Festival
    0.83
     seminars
    0.82
    Activations Density 1.057%

    No Known Activations