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. 5219
    Prev
    Next
    INDEX
    Explanations

    elements related to programs or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific programs or initiatives

    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
     stake
    -0.72
    vg
    -0.69
    AAAA
    -0.69
    thal
    -0.68
    pg
    -0.67
     treacherous
    -0.67
     vapor
    -0.61
    structed
    -0.61
    usalem
    -0.60
     Chic
    -0.59
    POSITIVE LOGITS
     programme
    1.30
     programmes
    1.26
     Programme
    1.22
    mable
    0.89
    eers
    0.82
    ĸļ
    0.81
    oleon
    0.81
     programs
    0.79
     program
    0.78
    eering
    0.77
    Activations Density 0.009%

    No Known Activations