© 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. 10-RES-JB
    11. 11561
    Prev
    Next
    INDEX
    Explanations

    references to the self or first-person perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of the name "Brammeister"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pole
    -0.76
    roads
    -0.73
    hips
    -0.70
    rama
    -0.68
    rieved
    -0.67
    ourcing
    -0.63
    iary
    -0.62
    iosity
    -0.60
    paralle
    -0.60
    ultz
    -0.60
    POSITIVE LOGITS
    asure
    1.27
    anwhile
    1.20
    lda
    1.13
    zzo
    1.11
    ister
    1.07
    leon
    1.04
    asured
    1.04
    adows
    1.02
    asuring
    1.02
    adow
    1.01
    Activations Density 0.030%

    No Known Activations