© 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. 6-RES-JB
    11. 14516
    Prev
    Next
    INDEX
    Explanations

    references to falling figuratively and literally

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fall"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zee
    -0.72
    eers
    -0.69
    iliary
    -0.68
    ilation
    -0.68
    ledge
    -0.67
    cius
    -0.63
    keeping
    -0.61
    folios
    -0.61
    urated
    -0.58
    facts
    -0.58
    POSITIVE LOGITS
    acies
    1.04
     asleep
    1.01
    opian
    0.99
    owship
    0.95
    ows
    0.84
     overboard
    0.76
    ujah
    0.76
    avier
    0.75
    acious
    0.75
     prey
    0.75
    Activations Density 0.032%

    No Known Activations