© 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 EvalsExportsAPI 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. 3-RES-JB
    11. 3709
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to misrepresentation, manipulation, and distortion

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of distortion and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uscript
    -0.74
    ept
    -0.73
    rol
    -0.72
    APTER
    -0.72
    EA
    -0.70
    sat
    -0.69
    ilk
    -0.68
     Prospect
    -0.67
    psc
    -0.66
    cript
    -0.66
    POSITIVE LOGITS
     distortion
    1.22
     distort
    1.14
     distortions
    1.13
     distorted
    0.96
    adoes
    0.78
     havoc
    0.74
     mund
    0.69
    ibly
    0.69
    usional
    0.68
     overest
    0.67
    Activations Density 0.010%

    No Known Activations