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. 8-RES-JB
    6. 5188
    Prev
    Next
    INDEX
    Explanations

    people's surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĶĢâĶĢ
    -0.76
    ModLoader
    -0.74
     underwater
    -0.71
     millennials
    -0.66
    etheless
    -0.66
     LeBron
    -0.65
     Rebirth
    -0.64
     Hurricane
    -0.64
     Gaga
    -0.63
     Galileo
    -0.63
    POSITIVE LOGITS
    ansky
    1.10
    stad
    1.06
    atz
    1.06
    zen
    1.06
    inger
    1.06
    nick
    1.04
    inski
    1.04
    burn
    1.03
    sell
    1.03
    anson
    1.02
    Activations Density 0.246%

    No Known Activations