© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12095
    Prev
    Next
    INDEX
    Explanations

    words related to mistakes, miscalculations, and unintended consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to misguided or unintended actions and their consequences

    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
     Surviv
    -0.76
    boats
    -0.71
    boat
    -0.71
    kees
    -0.70
     cryst
    -0.69
    rawling
    -0.68
    ordon
    -0.68
    ailable
    -0.67
    annis
    -0.66
    listed
    -0.66
    POSITIVE LOGITS
     misguided
    0.91
     misplaced
    0.74
    alus
    0.74
     folly
    0.73
    elligent
    0.70
    Reloaded
    0.70
     glances
    0.69
     innocence
    0.69
     impulse
    0.68
     Hubble
    0.68
    Activations Density 0.012%

    No Known Activations