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

    Neuronpedia

    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. 6-RES-JB
    11. 17122
    Prev
    Next
    INDEX
    Explanations

    adjectives related to a negative or unwanted context

    oai_token-act-pair · gpt-3.5-turbo

    terms that denote significant or problematic qualities and categories in various contexts

    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
    Ö¼
    -0.70
    veyard
    -0.70
    xual
    -0.67
    swer
    -0.66
    uana
    -0.63
    mma
    -0.63
    KN
    -0.62
     Myster
    -0.61
    Thumbnail
    -0.60
    agame
    -0.59
    POSITIVE LOGITS
     amounts
    0.92
     portions
    0.89
     quantities
    0.88
     burdens
    0.83
     messages
    0.82
     objects
    0.82
     passages
    0.78
     segments
    0.77
     items
    0.77
     copies
    0.77
    Activations Density 0.445%

    No Known Activations