© 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. 15157
    Prev
    Next
    INDEX
    Explanations

    statements related to costs and financial implications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to high costs or expenses

    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
    vez
    -0.74
     Ago
    -0.70
     nod
    -0.69
    dar
    -0.69
    thia
    -0.69
    Style
    -0.68
    dit
    -0.67
    ropolitan
    -0.64
    ologue
    -0.64
    marriage
    -0.63
    POSITIVE LOGITS
     incurred
    1.29
     outweigh
    1.27
     outwe
    1.24
     negligible
    1.23
     deductible
    1.09
     exceed
    0.99
     reimb
    0.96
     offset
    0.94
     minimal
    0.92
     diminished
    0.91
    Activations Density 0.334%

    No Known Activations