© 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. 6492
    Prev
    Next
    INDEX
    Explanations

    greetings and addresses to a group

    oai_token-act-pair · gpt-3.5-turbo

    references to a general audience or group of people

    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
     Kamp
    -0.67
     himself
    -0.64
     Stalin
    -0.63
     Churchill
    -0.61
     course
    -0.58
    hibition
    -0.58
     fasc
    -0.58
     Edu
    -0.57
     Worse
    -0.57
     Niet
    -0.57
    POSITIVE LOGITS
    rats
    0.78
    Interested
    0.77
    members
    0.74
    Ü
    0.74
    hesda
    0.72
    uesday
    0.69
     gathered
    0.68
    intern
    0.66
    RIP
    0.66
     alike
    0.65
    Activations Density 0.110%

    No Known Activations