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. 9-RES-JB
    6. 9484
    Prev
    Next
    INDEX
    Explanations

    references related to social media accounts or user handles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    discrimination
    -0.73
    380
    -0.70
    rimination
    -0.66
     conceal
    -0.66
     barrier
    -0.65
    emb
    -0.64
    mental
    -0.64
    è¦ļéĨĴ
    -0.63
    iggurat
    -0.63
    und
    -0.63
    POSITIVE LOGITS
     @
    1.56
     (@
    1.28
    @
    1.19
     "@
    1.03
     vs
    1.00
    (&
    0.91
     Vs
    0.90
    @@@@
    0.89
     @@
    0.85
     <@
    0.84
    Activations Density 0.096%

    No Known Activations