© 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. 9-RES-JB
    11. 7461
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "first time" followed by a verb or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "first" and its variations, indicating occurrences of new events or admissions

    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
    */(
    -0.74
    ooks
    -0.71
    jon
    -0.71
    redients
    -0.70
    apons
    -0.70
    ourage
    -0.68
    iolet
    -0.67
    styles
    -0.67
    acent
    -0.66
    Methods
    -0.66
    POSITIVE LOGITS
     time
    1.10
     indication
    1.07
     occasion
    1.02
     foray
    1.02
     installment
    0.99
     instance
    0.97
     occurrence
    0.91
     anniversary
    0.91
     appearance
    0.91
     sighting
    0.89
    Activations Density 0.082%

    No Known Activations