© 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. 8-RES-JB
    11. 6534
    Prev
    Next
    INDEX
    Explanations

    questions or tasks listed in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    references to 'things' in various 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
    ipient
    -0.75
    RAFT
    -0.69
     IEEE
    -0.68
    geon
    -0.67
    estro
    -0.65
     Endless
    -0.64
    claimer
    -0.62
    ibal
    -0.61
    oti
    -0.60
    ardo
    -0.60
    POSITIVE LOGITS
     happen
    0.95
     happening
    0.90
    thinkable
    0.76
     happ
    0.75
     dislike
    0.71
     sauces
    0.69
     wrong
    0.68
     interact
    0.67
    animate
    0.65
     cov
    0.64
    Activations Density 0.369%

    No Known Activations