© 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. 9-RES-JB
    6. 2780
    Prev
    Next
    INDEX
    Explanations

    characters and sounds, especially in a repeated manner

    oai_token-act-pair · gpt-3.5-turbo

    repeated vowel sounds or long stretches of repeated characters

    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
     Prospect
    -0.81
     Carth
    -0.77
     errone
    -0.77
     princ
    -0.76
     behavioural
    -0.71
     surn
    -0.70
     statically
    -0.69
     Lever
    -0.69
     Mechdragon
    -0.69
     suppl
    -0.69
    POSITIVE LOGITS
    aaaa
    1.35
    oooo
    1.35
    AAAA
    1.32
    ooo
    1.32
    !!!!!
    1.31
    AAA
    1.29
    aaa
    1.27
    mmmm
    1.24
    AAAAAAAA
    1.23
    oooooooo
    1.23
    Activations Density 0.097%

    No Known Activations