© 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. 6-RES-JB
    11. 11995
    Prev
    Next
    INDEX
    Explanations

    specific mentions of entities followed by possessive markers (such as "'s")

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "s" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rounds
    -0.71
     Pharaoh
    -0.70
     Slate
    -0.69
     Slug
    -0.66
     Reef
    -0.64
     Seas
    -0.64
    Film
    -0.63
     Salon
    -0.61
     Ago
    -0.61
    PN
    -0.61
    POSITIVE LOGITS
    selves
    1.14
    ELF
    1.05
     own
    0.96
    ources
    0.94
    outhern
    0.88
    ustainable
    0.87
    atically
    0.85
    oes
    0.83
    essions
    0.82
    leeve
    0.81
    Activations Density 0.155%

    No Known Activations