© 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. 7-RES-JB
    11. 12684
    Prev
    Next
    INDEX
    Explanations

    blame or accusations being made against someone or some entity

    oai_token-act-pair · gpt-3.5-turbo

    instances of accusations against individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kos
    -0.69
     ~/
    -0.68
    ominated
    -0.64
    die
    -0.64
    pleted
    -0.63
     survives
    -0.63
    »Ĵ
    -0.61
    gat
    -0.61
     LIFE
    -0.61
    daq
    -0.61
    POSITIVE LOGITS
     unfairly
    0.99
     inappropriately
    0.90
     hypocritical
    0.81
     misleading
    0.80
     insensitive
    0.79
     unnecessarily
    0.78
     prejud
    0.77
     biased
    0.77
     irresponsible
    0.77
     dishonest
    0.77
    Activations Density 0.515%

    No Known Activations