© 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. 4-RES-JB
    11. 6289
    Prev
    Next
    INDEX
    Explanations

    adjectives with morally or emotionally charged undertones

    oai_token-act-pair · gpt-3.5-turbo

    negative or critical language directed at people or groups

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

    No Comments

    Negative Logits
    uana
    -0.55
    vous
    -0.54
     conclud
    -0.49
     fundament
    -0.49
     Musical
    -0.48
    idate
    -0.48
     âĶľ
    -0.48
     Ern
    -0.47
    ItemThumbnailImage
    -0.46
     Carbuncle
    -0.46
    POSITIVE LOGITS
    pes
    0.57
    bol
    0.55
    quit
    0.50
    heartedly
    0.49
    istries
    0.49
    obs
    0.47
    hes
    0.46
    coins
    0.46
     sqor
    0.45
    ickets
    0.44
    Activations Density 1.560%

    No Known Activations