© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 10822
    Prev
    Next
    INDEX
    Explanations

    phrases related to causal relationships (e.g., "if," "because"), especially when followed by a condition that triggers an effect

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases that indicate contrast or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ether
    -0.93
    esi
    -0.76
    orthy
    -0.69
     Dunk
    -0.65
    ente
    -0.65
    SourceFile
    -0.64
    Merit
    -0.62
    apest
    -0.61
    housing
    -0.61
    abs
    -0.58
    POSITIVE LOGITS
     accordingly
    0.76
    pires
    0.75
     rewarded
    0.71
    etheless
    0.69
     thereof
    0.69
     consequently
    0.68
     importantly
    0.68
    é¾įå
    0.68
     ensuing
    0.67
     guessed
    0.67
    Activations Density 0.191%

    No Known Activations