© 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. 0-RES-JB
    11. 7832
    Prev
    Next
    INDEX
    Explanations

    terms related to biographies or biopics

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "topic" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Beat
    -0.63
     separates
    -0.62
     registers
    -0.61
     incre
    -0.60
     subs
    -0.59
     inval
    -0.59
     Crim
    -0.58
     souls
    -0.58
     batters
    -0.58
     rows
    -0.57
    POSITIVE LOGITS
    opic
    4.80
    opia
    2.05
    opy
    1.99
    opes
    1.67
    ope
    1.46
    oping
    1.33
    oped
    1.30
    opian
    1.26
    op
    1.14
    opter
    1.13
    Activations Density 0.012%

    No Known Activations