© 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. 4-RES-JB
    11. 3616
    Prev
    Next
    INDEX
    Explanations

    words related to faults or flaws

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fault" and its variations

    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
    gdala
    -0.84
    glers
    -0.82
     Flavoring
    -0.75
    atown
    -0.74
    ×IJ
    -0.74
    isphere
    -0.74
    Interstitial
    -0.73
    ======
    -0.71
    TERN
    -0.70
    HCR
    -0.70
    POSITIVE LOGITS
    ault
    1.12
    aults
    0.98
    eus
    0.85
    lain
    0.79
    essor
    0.79
    ier
    0.78
    ily
    0.73
    ufact
    0.72
    minster
    0.72
    gow
    0.71
    Activations Density 0.013%

    No Known Activations