© 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. 6-RES-JB
    11. 9641
    Prev
    Next
    INDEX
    Explanations

    phrases indicating incorrect or inaccurate information or understanding

    oai_token-act-pair · gpt-3.5-turbo

    instances of mischaracterization or misrepresentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaries
    -0.76
    urable
    -0.72
    tar
    -0.70
    winner
    -0.68
    cedes
    -0.67
    Lago
    -0.66
    iary
    -0.66
    hya
    -0.66
    zens
    -0.66
    contained
    -0.65
    POSITIVE LOGITS
     underest
    0.74
     mistaken
    0.74
     impression
    0.74
    é¾įå
    0.73
     mistake
    0.72
     NX
    0.71
     mistakes
    0.70
     perceptions
    0.68
    Newsletter
    0.68
     Poles
    0.68
    Activations Density 0.231%

    No Known Activations