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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 3478
    Prev
    Next
    INDEX
    Explanations

    verbs related to cognitive processes, such as inhibition, recognition, and understanding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cognitive and emotional processes in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ranch
    -0.79
     Shogun
    -0.77
     Manor
    -0.76
     Franch
    -0.76
    phalt
    -0.75
     Profit
    -0.75
    grim
    -0.74
    ufact
    -0.74
     Bung
    -0.74
     Armageddon
    -0.74
    POSITIVE LOGITS
     stimuli
    1.55
     cues
    1.32
     perceptual
    1.20
     behaviors
    1.19
     stimulus
    1.13
     cognition
    1.12
     elic
    1.12
     cognitive
    1.10
     elicit
    1.06
     verbal
    1.05
    Activations Density 0.631%

    No Known Activations