© 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. 9313
    Prev
    Next
    INDEX
    Explanations

    words related to government assistance programs

    oai_token-act-pair · gpt-3.5-turbo

    references to food stamps and financial support programs

    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
     Stras
    -0.77
     Ae
    -0.74
     Beau
    -0.73
    SOURCE
    -0.73
    semble
    -0.72
     Argon
    -0.69
    IENT
    -0.65
     Jenner
    -0.64
     Bucc
    -0.64
     RIS
    -0.63
    POSITIVE LOGITS
     stamps
    1.17
     stamp
    0.86
    pak
    0.76
    uity
    0.75
    icket
    0.72
     stripe
    0.71
    cards
    0.71
    eding
    0.70
    manship
    0.70
    ishing
    0.69
    Activations Density 0.011%

    No Known Activations