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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9219
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions, particularly impeachment

    oai_token-act-pair · gpt-3.5-turbo

    words related to immersion or immersive 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
     Skydragon
    -0.64
     Frey
    -0.63
    undy
    -0.63
     vine
    -0.60
     decom
    -0.59
    },"
    -0.57
    posted
    -0.57
     kernels
    -0.56
     scree
    -0.56
    bara
    -0.55
    POSITIVE LOGITS
    achment
    0.84
    ãĥ¼ãĤ¯
    0.77
    lycer
    0.76
    acl
    0.75
    agement
    0.73
    uments
    0.73
    imum
    0.72
    ortal
    0.71
    imate
    0.70
    ás
    0.70
    Activations Density 0.075%

    No Known Activations