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. 5807
    Prev
    Next
    INDEX
    Explanations

    references to camera resolutions and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of megapixels, particularly in the context of cameras

    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
    ebted
    -0.94
    nces
    -0.91
    sbm
    -0.77
    taboola
    -0.76
    Else
    -0.75
    idad
    -0.75
    mberg
    -0.71
    worldly
    -0.70
    zona
    -0.68
    perse
    -0.67
    POSITIVE LOGITS
    EG
    1.16
    ropri
    0.90
    olicy
    0.90
    IC
    0.88
    alm
    0.88
    ixels
    0.88
    OA
    0.87
    UV
    0.84
    rompt
    0.82
    MP
    0.81
    Activations Density 0.013%

    No Known Activations