© 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. 6239
    Prev
    Next
    INDEX
    Explanations

    phrases expressing admiration or preference

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of the word "the" in various contexts

    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
     accordingly
    -0.76
     according
    -0.75
    strate
    -0.73
    SPONSORED
    -0.73
    ontent
    -0.70
     namely
    -0.69
     thereby
    -0.69
    IFA
    -0.69
    alion
    -0.68
    owned
    -0.67
    POSITIVE LOGITS
     idea
    1.43
     notion
    1.19
     possibility
    1.08
     opportunity
    1.02
     concept
    1.01
     prospect
    0.99
     latter
    0.98
     fact
    0.98
     simplicity
    0.94
     finer
    0.93
    Activations Density 0.212%

    No Known Activations