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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9939
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative emotions, such as disillusionment, dissatisfaction, frustration, and disappointment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative sentiments and feelings of disappointment or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ozo
    -0.74
    atural
    -0.64
    ahead
    -0.62
    eworks
    -0.61
    bold
    -0.61
    opped
    -0.60
    skirts
    -0.60
    uin
    -0.59
    ann
    -0.59
    alez
    -0.59
    POSITIVE LOGITS
    ment
    1.09
    ingly
    1.03
    ments
    0.98
    mented
    0.89
    ient
    0.86
    actory
    0.82
     with
    0.79
    atisf
    0.79
    ienced
    0.77
    ful
    0.77
    Activations Density 0.094%

    No Known Activations