© 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. 8-RES-JB
    6. 6956
    Prev
    Next
    INDEX
    Explanations

    references to names ending with 'm'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "m" in the text

    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
     pitch
    -0.76
    DragonMagazine
    -0.68
     giveaway
    -0.65
     behav
    -0.64
     foul
    -0.60
     drive
    -0.59
     tipped
    -0.58
     freeze
    -0.57
    EStream
    -0.57
     scholarship
    -0.55
    POSITIVE LOGITS
    ichael
    1.27
    otor
    1.23
    ortal
    1.22
    obil
    1.21
    obiles
    1.19
    useum
    1.16
    ixed
    1.11
    aiden
    1.10
    asonic
    1.10
    ortality
    1.10
    Activations Density 0.066%

    No Known Activations