© 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. 4-RES-JB
    11. 7428
    Prev
    Next
    INDEX
    Explanations

    phrases related to programs or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to various programs or initiatives

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

    No Comments

    Negative Logits
     stake
    -0.76
    Jr
    -0.65
    hiro
    -0.64
    thal
    -0.62
    vg
    -0.62
    pg
    -0.61
    çĶŁ
    -0.61
    unts
    -0.61
     treacherous
    -0.60
     vapor
    -0.59
    POSITIVE LOGITS
     programmes
    1.20
     programme
    1.17
     Programme
    1.12
    mable
    0.99
    matic
    0.92
    ĸļ
    0.89
    matically
    0.87
    eers
    0.87
    caster
    0.82
    casters
    0.79
    Activations Density 0.011%

    No Known Activations