© 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. 1-RES-JB
    11. 24154
    Prev
    Next
    INDEX
    Explanations

    different kinds of items or categories

    oai_token-act-pair · gpt-3.5-turbo

    references to various categories or types of entities

    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
    yer
    -0.66
    heid
    -0.65
    bay
    -0.65
     Yel
    -0.64
    edia
    -0.64
    phot
    -0.63
    inal
    -0.63
    LAN
    -0.62
    ITNESS
    -0.62
    ouston
    -0.60
    POSITIVE LOGITS
    etter
    1.00
    etting
    0.97
     kinds
    0.87
     sorts
    0.80
    pace
    0.76
    heartedly
    0.73
     coerc
    0.71
    ername
    0.70
    omething
    0.70
    ometimes
    0.70
    Activations Density 0.008%

    No Known Activations