Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3784
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives that describe the physical or emotional state of something or someone

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional states and psychological conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quotas
    -0.75
    tl
    -0.75
     Architects
    -0.74
     successors
    -0.72
     Publishers
    -0.72
     diversity
    -0.70
     franchises
    -0.70
    icion
    -0.69
     Laws
    -0.69
     Peoples
    -0.69
    POSITIVE LOGITS
     intoxicated
    1.64
     asleep
    1.55
     depressed
    1.49
     unconscious
    1.46
     nervous
    1.46
     agitated
    1.45
     drunk
    1.42
     frightened
    1.42
     distraught
    1.42
     awake
    1.41
    Activations Density 0.293%

    No Known Activations