© 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. 8-RES-JB
    6. 23685
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific condition or state of being

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azines
    -0.74
    iest
    -0.73
    dad
    -0.63
    iaries
    -0.63
     Branch
    -0.60
    ittens
    -0.60
    handle
    -0.59
     Huntington
    -0.59
    ilk
    -0.59
     answer
    -0.59
    POSITIVE LOGITS
     sorts
    1.22
     theirs
    0.82
     unparalleled
    0.81
     heightened
    0.77
     contrasts
    0.74
    ãĥİ
    0.74
     impunity
    0.73
     obscurity
    0.72
     exclus
    0.72
     disadvantage
    0.71
    Activations Density 0.183%

    No Known Activations