© 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. 3-RES-JB
    6. 15057
    Prev
    Next
    INDEX
    Explanations

    terms related to extremes of behavior, such as overly controlling, ambitious, aggressive, permissive, or influential

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "overly" and its related forms, indicating excessive qualities or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iens
    -0.81
    itudinal
    -0.77
     Tycoon
    -0.72
    uments
    -0.70
     Bullets
    -0.70
    =-=-=-=-=-=-=-=-
    -0.70
     Conservation
    -0.68
    arta
    -0.68
    raltar
    -0.68
    ories
    -0.68
    POSITIVE LOGITS
     simplistic
    0.85
     optimistic
    0.80
     overd
    0.78
     intoxicated
    0.77
     sensitive
    0.76
     complicate
    0.76
    assi
    0.75
     overpowered
    0.75
     burdens
    0.75
     aggressive
    0.75
    Activations Density 0.007%

    No Known Activations