© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-JB
    11. 21662
    Prev
    Next
    INDEX
    Explanations

    group names or acronyms that likely pertain to an organization or movement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "FE" and its variations, indicating a repetitive reference to a specific topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assian
    -0.79
    agically
    -0.75
    appropriately
    -0.66
    race
    -0.66
     Clever
    -0.64
     Siren
    -0.64
    taker
    -0.63
    worthy
    -0.63
     Ducks
    -0.61
    pop
    -0.61
    POSITIVE LOGITS
    FE
    1.21
     FE
    1.13
    ATURES
    1.06
    VE
    1.06
    ruary
    0.95
    ATURE
    0.92
    BR
    0.90
    EMBER
    0.90
    VERS
    0.88
    VER
    0.88
    Activations Density 0.006%

    No Known Activations