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. 22086
    Prev
    Next
    INDEX
    Explanations

    terms related to subscription options and user agreements

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "at" indicating locations or timing

    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
    pher
    -0.84
    Pac
    -0.70
    HAM
    -0.64
    ngth
    -0.64
    onne
    -0.62
    Bloom
    -0.60
    ynthesis
    -0.60
    jury
    -0.59
    pan
    -0.59
    PAC
    -0.58
    POSITIVE LOGITS
     preferences
    0.71
    ributes
    0.71
     request
    0.70
     least
    0.66
    ¶æ
    0.65
     snipp
    0.65
     variance
    0.64
     invite
    0.63
    ~~~~
    0.62
     preference
    0.62
    Activations Density 0.027%

    No Known Activations