© 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. 3344
    Prev
    Next
    INDEX
    Explanations

    words related to inadequacy or lack of skill

    oai_token-act-pair · gpt-3.5-turbo

    terms related to failure or inefficiency

    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
    ozo
    -0.83
    forward
    -0.80
    encers
    -0.77
    venue
    -0.76
    antam
    -0.75
    weight
    -0.72
    bour
    -0.71
    alde
    -0.70
    waves
    -0.69
    horn
    -0.68
    POSITIVE LOGITS
     botched
    1.15
     mishand
    1.08
     incompetence
    1.08
     incompetent
    1.04
     incompet
    0.96
     inept
    0.94
     bung
    0.89
     failures
    0.84
     goof
    0.75
     miser
    0.73
    Activations Density 0.024%

    No Known Activations