© 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. 16988
    Prev
    Next
    INDEX
    Explanations

    phrases starting with a special character sequence 'Ċ' followed by numeric values

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial statistics or economic conditions

    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
     localized
    -0.72
     Palo
    -0.69
     dime
    -0.69
     honors
    -0.68
     someday
    -0.68
     favorably
    -0.67
     UCS
    -0.67
    boro
    -0.66
     Americ
    -0.65
    gins
    -0.64
    POSITIVE LOGITS
    Labour
    1.14
    Shape
    0.96
    Scotland
    0.94
    Britain
    0.93
    Scroll
    0.91
    England
    0.91
    Liverpool
    0.90
     mould
    0.86
    Article
    0.85
    BBC
    0.83
    Activations Density 0.407%

    No Known Activations