© 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. 20334
    Prev
    Next
    INDEX
    Explanations

    information about musical performances, including details about band members and their instruments

    oai_token-act-pair · gpt-3.5-turbo

    references to music and performers

    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
     civilisation
    -0.72
    SOURCE
    -0.72
    Rew
    -0.70
    INESS
    -0.65
     Racial
    -0.64
     ®
    -0.63
     lifestyles
    -0.60
     realities
    -0.60
     Policies
    -0.60
     totality
    -0.59
    POSITIVE LOGITS
     likewise
    0.96
     Leilan
    0.81
    itto
    0.78
     similarly
    0.74
    zona
    0.74
     cameo
    0.74
     consolation
    0.72
    ebus
    0.70
    alli
    0.70
    reditary
    0.70
    Activations Density 0.797%

    No Known Activations