© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 20006
    Prev
    Next
    INDEX
    Explanations

    verbs related to falling asleep or falling down

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fell" and its variations related to falling or losing consciousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iola
    -0.71
     Exclusive
    -0.68
    eers
    -0.65
     Scope
    -0.62
     extant
    -0.61
    chn
    -0.60
    ctive
    -0.58
     stripe
    -0.58
     Moder
    -0.58
     QC
    -0.57
    POSITIVE LOGITS
     asleep
    1.43
     overboard
    1.07
    atio
    0.95
     victim
    0.93
     pregnant
    0.90
    opian
    0.90
    owship
    0.90
     prey
    0.89
     unconscious
    0.88
     into
    0.88
    Activations Density 0.090%

    No Known Activations