© 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. 1-RES-JB
    11. 24283
    Prev
    Next
    INDEX
    Explanations

    phrases related to geologic events and time periods

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that connect ideas or phrases

    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
    Lex
    -0.68
     princip
    -0.67
    meier
    -0.66
     Chev
    -0.65
    cyclopedia
    -0.63
    GUI
    -0.63
    Ped
    -0.62
    apo
    -0.62
    Cas
    -0.62
     Ange
    -0.61
    POSITIVE LOGITS
    scl
    0.85
    eenth
    0.79
    ition
    0.73
     blister
    0.69
     CLR
    0.68
    idth
    0.68
     rehe
    0.67
    akening
    0.66
    irk
    0.65
    ITION
    0.65
    Activations Density 0.000%

    No Known Activations