© 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. 0-RES-JB
    11. 4171
    Prev
    Next
    INDEX
    Explanations

    mentions of company names ending in 'Ltd'

    oai_token-act-pair · gpt-3.5-turbo

    references to business entities and limited companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     racial
    -0.68
     defense
    -0.63
     conservative
    -0.62
     offense
    -0.62
     bo
    -0.62
     undocumented
    -0.62
     tough
    -0.61
     health
    -0.61
     honorable
    -0.60
     reproductive
    -0.60
    POSITIVE LOGITS
     Ltd
    3.83
     LTD
    2.41
     Limited
    1.79
     LLP
    1.78
     LLC
    1.77
     Inc
    1.65
     LIMITED
    1.51
     Corp
    1.46
     Holdings
    1.42
     INC
    1.24
    Activations Density 0.013%

    No Known Activations