© 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. 4-RES-JB
    11. 9725
    Prev
    Next
    INDEX
    Explanations

    mentions of unlimited plans or services

    oai_token-act-pair · gpt-3.5-turbo

    references to unlimited plans or services

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

    No Comments

    Negative Logits
    bourg
    -0.78
    iquette
    -0.77
    acus
    -0.75
    alid
    -0.75
    ifice
    -0.74
    geist
    -0.73
    icho
    -0.73
    udic
    -0.72
    pillar
    -0.72
    ake
    -0.72
    POSITIVE LOGITS
     amounts
    1.07
     amount
    0.91
     access
    0.88
     unlimited
    0.85
     quantities
    0.84
     privileges
    0.75
     gratification
    0.71
     remission
    0.71
     bandwidth
    0.71
     quantity
    0.70
    Activations Density 0.013%

    No Known Activations