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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 7521
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Gabby" or variations of the name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name 'Gab'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sels
    -0.73
    \\\\\\\\\\\\\\\\
    -0.71
    selage
    -0.70
    lli
    -0.69
     slic
    -0.68
    terness
    -0.68
     detain
    -0.67
    ère
    -0.66
     tem
    -0.66
    ilogy
    -0.66
    POSITIVE LOGITS
     Gab
    3.80
    Gab
    2.24
     Britt
    1.39
     Gamb
    1.10
     Aub
    1.08
     Germ
    1.07
     Ivory
    1.07
     Mic
    1.05
     gib
    1.03
     Gib
    1.00
    Activations Density 0.033%

    No Known Activations