© 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. 3-RES-JB
    6. 7206
    Prev
    Next
    INDEX
    Explanations

    the word "thing" appearing in varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "a thing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inav
    -0.86
    cling
    -0.71
    cled
    -0.70
     largeDownload
    -0.68
    ervation
    -0.64
    resents
    -0.63
     anonymity
    -0.63
    avage
    -0.63
    cul
    -0.62
    oufl
    -0.61
    POSITIVE LOGITS
    iverse
    1.00
    Else
    0.93
     happened
    0.92
     happ
    0.90
     happening
    0.89
     happens
    0.86
     Valiant
    0.84
     happen
    0.76
     undone
    0.76
     else
    0.75
    Activations Density 0.039%

    No Known Activations