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. 15900
    Prev
    Next
    INDEX
    Explanations

    instances where permission is required or granted

    oai_token-act-pair · gpt-3.5-turbo

    mentions of permission

    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
    ulative
    -0.71
    ulz
    -0.69
    tal
    -0.66
    itched
    -0.65
     Revel
    -0.62
    oche
    -0.62
    utton
    -0.62
     Beet
    -0.61
     Sadd
    -0.61
    allion
    -0.61
    POSITIVE LOGITS
     permission
    1.06
    Reviewer
    0.89
     permissions
    0.89
     waivers
    0.83
     granted
    0.79
    uthor
    0.77
    ibl
    0.77
    essee
    0.75
    eous
    0.75
     clearance
    0.75
    Activations Density 0.014%

    No Known Activations