© 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. 7-RES-JB
    11. 12626
    Prev
    Next
    INDEX
    Explanations

    the word "ch" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ch"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERC
    -0.74
    GMT
    -0.68
     corrid
    -0.67
    ©¶æ
    -0.66
    PDATE
    -0.63
    berman
    -0.62
     rall
    -0.61
     Soy
    -0.60
     monarch
    -0.60
    ¥µ
    -0.59
    POSITIVE LOGITS
    icago
    1.22
    ampions
    1.19
    ambers
    1.18
    ampion
    1.12
    inese
    1.11
    aos
    1.08
    amps
    1.06
    ocolate
    1.06
    amber
    1.03
    icken
    1.02
    Activations Density 0.039%

    No Known Activations