© 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. 8-RES-JB
    11. 1928
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific style or aesthetic

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic or thematic styles

    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
    atoon
    -0.91
    ma
    -0.84
    arus
    -0.82
    wright
    -0.80
    arte
    -0.80
    ora
    -0.78
    emi
    -0.76
    osponsors
    -0.74
    liga
    -0.74
    ipedia
    -0.73
    POSITIVE LOGITS
     immersion
    0.77
     confinement
    0.76
     burial
    0.75
     closure
    0.75
     refinement
    0.75
     punishments
    0.73
     executions
    0.72
     extremism
    0.71
     landslide
    0.69
     separation
    0.69
    Activations Density 0.084%

    No Known Activations