© 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. 8-RES-JB
    11. 2708
    Prev
    Next
    INDEX
    Explanations

    words related to errors or imperfections

    oai_token-act-pair · gpt-3.5-turbo

    terms related to flaws, weaknesses, and deficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rollers
    -0.86
    amaz
    -0.74
    Ń·
    -0.73
    iversary
    -0.70
     Carbuncle
    -0.68
    da
    -0.68
    cow
    -0.66
    upt
    -0.65
    rontal
    -0.64
    ctors
    -0.63
    POSITIVE LOGITS
     weaknesses
    1.08
     flaws
    1.07
     inherent
    1.03
     flaw
    0.99
     plag
    0.96
     vulnerabilities
    0.91
     weakness
    0.84
     loopholes
    0.84
     vulner
    0.79
     deficiencies
    0.78
    Activations Density 0.085%

    No Known Activations