© 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. 20073
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to things that are cracked

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cracked" and its variations

    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
    amins
    -0.71
    alla
    -0.70
    enture
    -0.68
    folk
    -0.67
    ikk
    -0.66
    ¥µ
    -0.65
     Vanguard
    -0.64
     Dayton
    -0.63
    ista
    -0.63
    DK
    -0.63
    POSITIVE LOGITS
     cracking
    1.10
    pots
    1.08
     cracked
    1.06
     cracks
    0.87
     jaws
    0.85
    estamp
    0.79
    kered
    0.79
     crack
    0.76
    Berry
    0.74
    breakers
    0.73
    Activations Density 0.008%

    No Known Activations