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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 9455
    Prev
    Next
    INDEX
    Explanations

    references to publications or media sources

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases beginning with a comma

    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
    inson
    -0.72
    ine
    -0.67
    ary
    -0.67
    ole
    -0.66
    icultural
    -0.66
    -,
    -0.66
     ail
    -0.65
    estinal
    -0.64
    isy
    -0.64
    arah
    -0.63
    POSITIVE LOGITS
     LLC
    1.17
     Inc
    1.10
     Ltd
    1.05
     Kinnikuman
    0.95
     LLP
    0.87
    Magikarp
    0.85
    Inc
    0.76
     Brav
    0.74
     LTD
    0.73
    Gall
    0.72
    Activations Density 0.288%

    No Known Activations