© 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. 23470
    Prev
    Next
    INDEX
    Explanations

    words related to basic needs like utilities and groceries

    oai_token-act-pair · gpt-3.5-turbo

    references to essential services and products related to daily living

    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
    York
    -0.65
    vol
    -0.65
    gha
    -0.64
     CFR
    -0.64
    esan
    -0.63
    oct
    -0.63
    Code
    -0.62
    bra
    -0.61
    nee
    -0.60
    oÄŁ
    -0.60
    POSITIVE LOGITS
    mith
    1.19
    poons
    1.06
    terday
    1.00
    chool
    0.98
    ystem
    0.97
    ynthesis
    0.97
    paces
    0.96
    ourcing
    0.94
    heet
    0.92
    uits
    0.92
    Activations Density 0.077%

    No Known Activations