© 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. 8-RES-JB
    11. 2081
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "ah"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sound "ah."

    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
     Daredevil
    -0.67
    chnology
    -0.64
    itions
    -0.64
     suspic
    -0.64
     ital
    -0.63
     seiz
    -0.62
     secretaries
    -0.60
     gobl
    -0.59
     Collider
    -0.59
     insured
    -0.59
    POSITIVE LOGITS
    awk
    1.58
    awks
    1.49
    renheit
    1.35
    ttp
    1.24
    olics
    1.22
    aha
    1.14
    tml
    1.12
    ouse
    1.05
    orses
    1.05
    ouston
    0.98
    Activations Density 0.039%

    No Known Activations