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. 11-RES-JB
    6. 10507
    Prev
    Next
    INDEX
    Explanations

    numerical expressions related to time

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to time or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lation
    -0.57
    mers
    -0.56
    nered
    -0.56
    aler
    -0.55
    oles
    -0.55
     loaded
    -0.54
    ozy
    -0.52
    eller
    -0.51
    yles
    -0.51
    phasis
    -0.50
    POSITIVE LOGITS
    Reason
    0.59
    id
    0.58
    Return
    0.58
    ethe
    0.54
    çĭ
    0.54
    ID
    0.52
    hex
    0.52
     Planet
    0.51
    yd
    0.50
    Parameter
    0.50
    Activations Density 0.294%

    No Known Activations