© 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. 4364
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to individuals and their actions or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to awareness and knowledge of situations

    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
     Fal
    -0.71
    wik
    -0.67
    gard
    -0.65
     Vaughn
    -0.63
     Howell
    -0.63
     Yel
    -0.62
     dexter
    -0.62
     Eps
    -0.61
     Conquest
    -0.61
     Torrent
    -0.60
    POSITIVE LOGITS
    self
    0.92
    selves
    0.91
    LO
    0.80
    agos
    0.80
    rogen
    0.72
     could
    0.70
     gotta
    0.69
    OLD
    0.68
    OTA
    0.68
     own
    0.68
    Activations Density 0.226%

    No Known Activations