© 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. 1-RES-JB
    6. 5191
    Prev
    Next
    INDEX
    Explanations

    verbs related to abrupt downward movement or decrease

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fell" in various contexts

    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
    cius
    -0.76
     Elite
    -0.63
    ancial
    -0.62
    iveness
    -0.62
    ledge
    -0.62
    illin
    -0.61
    sic
    -0.60
    ervation
    -0.59
    ño
    -0.59
    ña
    -0.59
    POSITIVE LOGITS
    owship
    1.03
     asleep
    0.84
    ows
    0.83
     swoop
    0.77
    lasses
    0.76
    atio
    0.75
     falls
    0.75
    Fall
    0.73
     fell
    0.71
    opian
    0.70
    Activations Density 0.013%

    No Known Activations