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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 24155
    Prev
    Next
    INDEX
    Explanations

    text enclosed in single quotes

    oai_token-act-pair · gpt-3.5-turbo

    quoted strings and their related structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.89
    avorite
    -0.69
     Burnett
    -0.68
     Izan
    -0.67
     Planetary
    -0.67
     Leilan
    -0.66
     Alchemist
    -0.65
     Yamato
    -0.64
     Flore
    -0.63
     fundament
    -0.62
    POSITIVE LOGITS
    Interstitial
    1.21
    taboola
    1.07
     ',
    0.97
    neath
    0.90
    tis
    0.88
    MpServer
    0.86
     '.
    0.86
    outer
    0.82
    nos
    0.82
     '[
    0.79
    Activations Density 0.034%

    No Known Activations