© 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. 7655
    Prev
    Next
    INDEX
    Explanations

    passive verbs followed by actions or decisions made by different entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decision-making and assessments

    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
    âĢ¢âĢ¢
    -0.77
    inventoryQuantity
    -0.74
    hai
    -0.71
    ao
    -0.68
    ipation
    -0.68
    SPONSORED
    -0.67
    fal
    -0.66
    si
    -0.64
    uably
    -0.62
     syndrome
    -0.61
    POSITIVE LOGITS
     separately
    0.87
    actionDate
    0.80
    ascript
    0.76
     Proced
    0.75
     manually
    0.74
     proportional
    0.73
     confidential
    0.70
     carefully
    0.68
     centrally
    0.68
     staggered
    0.67
    Activations Density 0.410%

    No Known Activations