© 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. 1-RES-JB
    11. 10194
    Prev
    Next
    INDEX
    Explanations

    words related to negative actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles characteristics in various contexts

    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
    fired
    -0.70
    talk
    -0.63
     cropped
    -0.62
    ãĥīãĥ©
    -0.62
     flown
    -0.61
     notice
    -0.59
    fur
    -0.59
    lake
    -0.58
    deal
    -0.57
     vault
    -0.57
    POSITIVE LOGITS
    redients
    1.06
    ating
    0.96
    atable
    0.90
    ATING
    0.89
    tons
    0.89
    ulate
    0.85
    issance
    0.77
    ivalent
    0.77
    orically
    0.76
     Sorce
    0.76
    Activations Density 0.079%

    No Known Activations