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. 5-RES-JB
    6. 14841
    Prev
    Next
    INDEX
    Explanations

    phrases expressing commentary or opinions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I mean" indicating clarification or emphasis

    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
    ivo
    -0.77
    ND
    -0.74
    ema
    -0.73
    mage
    -0.69
    MpServer
    -0.68
    Mesh
    -0.67
    rive
    -0.67
    UF
    -0.65
    Engineers
    -0.65
    ishes
    -0.65
    POSITIVE LOGITS
     uh
    0.92
     yeah
    0.88
     technically
    0.73
     WHAT
    0.71
     dunno
    0.71
     wow
    0.66
     imagine
    0.64
    othing
    0.64
     Wow
    0.62
     yes
    0.61
    Activations Density 0.048%

    No Known Activations