© 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. 1-RES-JB
    11. 14224
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a part or segment of a larger whole

    oai_token-act-pair · gpt-3.5-turbo

    references to episodes or parts in a series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gifted
    -0.72
    urses
    -0.68
     mentally
    -0.67
     arms
    -0.63
     patterns
    -0.61
    anche
    -0.60
     throats
    -0.59
     framing
    -0.59
     speakers
    -0.59
     ceilings
    -0.59
    POSITIVE LOGITS
    icipated
    1.17
    part
    1.08
    ners
    1.03
    ition
    0.93
    icles
    0.91
    ially
    0.91
    nered
    0.89
    icular
    0.88
    icularly
    0.88
    ner
    0.87
    Activations Density 0.005%

    No Known Activations