© 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. 9283
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "blessing" at varying strengths

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "blessing" in various contexts

    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
    pson
    -0.74
    arij
    -0.70
    otive
    -0.69
    swick
    -0.68
    chrome
    -0.67
    encers
    -0.67
    arers
    -0.66
    entin
    -0.66
    issues
    -0.64
    parts
    -0.63
    POSITIVE LOGITS
     Bless
    1.16
     blessings
    1.09
     blessing
    1.07
     bless
    1.03
     Blessing
    0.91
     bestowed
    0.91
     goodbye
    0.82
     decree
    0.73
    uitous
    0.73
    bringer
    0.71
    Activations Density 0.011%

    No Known Activations