© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14926
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing negative emotions such as disappointment, frustration, and exasperation

    oai_token-act-pair · gpt-3.5-turbo

    words related to emotional reactions or states of distress

    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
    glas
    -0.81
     faire
    -0.78
     reorgan
    -0.75
     appropriated
    -0.74
    vernment
    -0.73
    ©¶æ
    -0.72
    ascript
    -0.72
     livest
    -0.72
     guided
    -0.71
     lighter
    -0.69
    POSITIVE LOGITS
    ingly
    0.99
     Anger
    0.78
     Beir
    0.78
    ly
    0.75
     Dak
    0.74
    atically
    0.72
    LY
    0.72
    vu
    0.71
    ciating
    0.71
     Clown
    0.71
    Activations Density 0.098%

    No Known Activations