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. 2-RES-JB
    6. 22799
    Prev
    Next
    INDEX
    Explanations

    mentions of minimalism or minimal elements in descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to minimalism or minimal qualities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Report
    -0.75
    ravings
    -0.70
    å°Ĩ
    -0.69
    Reviewed
    -0.67
    CHQ
    -0.67
    Ranked
    -0.65
    Building
    -0.65
    iership
    -0.64
    Lord
    -0.64
    spr
    -0.64
    POSITIVE LOGITS
    etheless
    1.10
     amount
    0.84
    istic
    0.84
    ism
    0.82
     amounts
    0.82
     minimal
    0.81
    ocre
    0.78
     shorts
    0.77
    istically
    0.77
    isite
    0.77
    Activations Density 0.006%

    No Known Activations