© 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. 1-RES-JB
    11. 23997
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific companies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Tesla

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Doe
    -0.71
     Maiden
    -0.70
    ACTED
    -0.69
     Reign
    -0.69
     IRC
    -0.67
     Opinion
    -0.65
     Lisbon
    -0.65
     Washington
    -0.64
    icago
    -0.64
    nesota
    -0.64
    POSITIVE LOGITS
    Tes
    1.45
     Tes
    1.22
    terness
    1.01
    ©¶æ¥µ
    0.98
    heed
    0.96
    hiba
    0.96
     challeng
    0.91
     millenn
    0.89
     corrid
    0.87
    ween
    0.86
    Activations Density 0.006%

    No Known Activations