© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 4372
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or official processes

    oai_token-act-pair · gpt-3.5-turbo

    references to formal processes and structures, particularly involving access and permissions related to data and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nai
    -0.79
    ournal
    -0.72
     worshipped
    -0.70
    utherford
    -0.64
     disliked
    -0.64
    ottest
    -0.64
    tall
    -0.63
    ignty
    -0.62
    olerance
    -0.59
     Prix
    -0.59
    POSITIVE LOGITS
     prism
    1.05
     intermediary
    1.00
     channels
    0.98
     intermedi
    0.93
     lens
    0.87
     mediation
    0.87
     mechanisms
    0.79
     proxies
    0.79
     guise
    0.77
     conduit
    0.76
    Activations Density 0.235%

    No Known Activations