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. 20324
    Prev
    Next
    INDEX
    Explanations

    IP addresses

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and related references in a technical or statistical context

    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
    arist
    -0.77
    illon
    -0.75
    orical
    -0.74
     Lama
    -0.74
    enance
    -0.72
    ered
    -0.68
    furt
    -0.66
     Aval
    -0.66
    illac
    -0.66
    arnaev
    -0.66
    POSITIVE LOGITS
    cffff
    0.94
    ÏĤ
    0.90
    rencies
    0.84
    bably
    0.81
    nown
    0.81
    GBT
    0.80
    oshenko
    0.74
    essed
    0.72
    utions
    0.71
    idia
    0.71
    Activations Density 0.029%

    No Known Activations