© 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. 2-RES-JB
    11. 9082
    Prev
    Next
    INDEX
    Explanations

    negative attributes or qualities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of negativity or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.80
    arov
    -0.76
    ynthesis
    -0.73
    ovember
    -0.73
    hens
    -0.73
    ktop
    -0.72
    illation
    -0.71
    ellation
    -0.71
    agos
    -0.70
    Revolution
    -0.69
    POSITIVE LOGITS
    dest
    0.98
     karma
    0.88
    enough
    0.80
     bye
    0.80
    dies
    0.78
     vib
    0.77
     Samar
    0.77
     enough
    0.76
     undermin
    0.75
    die
    0.74
    Activations Density 0.020%

    No Known Activations