© 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. 4-RES-JB
    11. 673
    Prev
    Next
    INDEX
    Explanations

    the word "Me"

    oai_token-act-pair · gpt-3.5-turbo

    the mention of the speaker or first-person perspective, especially referring to themselves

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

    No Comments

    Negative Logits
    paralle
    -0.76
    pole
    -0.73
    raper
    -0.69
    medium
    -0.66
    kefeller
    -0.66
    itialized
    -0.64
    */(
    -0.64
    edged
    -0.63
     pend
    -0.63
     fragmentation
    -0.62
    POSITIVE LOGITS
    asures
    1.18
    asured
    1.10
    cca
    1.09
    asuring
    1.08
    eting
    1.06
    asure
    1.06
    aning
    1.05
    zzo
    1.05
    adows
    0.95
    adow
    0.90
    Activations Density 0.015%

    No Known Activations