© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 13791
    Prev
    Next
    INDEX
    Explanations

    combinations of the words "and" or "or" with other words

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and words that signify continuation or addition in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledged
    -0.67
     Lank
    -0.66
     Beam
    -0.65
    isite
    -0.63
    atis
    -0.61
    oteric
    -0.61
    termination
    -0.60
    allo
    -0.60
    ortium
    -0.60
    ellar
    -0.58
    POSITIVE LOGITS
     behave
    0.77
    othe
    0.72
     inspire
    0.68
    vere
    0.68
     evolve
    0.67
     pray
    0.67
     interact
    0.66
    mor
    0.66
     obey
    0.65
     breathe
    0.65
    Activations Density 0.257%

    No Known Activations