© 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. 734
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "nature" describing various aspects of a situation or process

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the characteristics or qualities of various subjects

    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
    rom
    -0.76
    oned
    -0.73
    itone
    -0.70
    ogun
    -0.70
     Sutherland
    -0.69
    rican
    -0.68
    oning
    -0.68
    visors
    -0.67
     balcon
    -0.67
    inis
    -0.67
    POSITIVE LOGITS
    tenance
    0.78
     quo
    0.72
    uality
    0.70
    ality
    0.69
    ForgeModLoader
    0.67
    ouf
    0.67
     insepar
    0.66
    %%%%
    0.66
     incarn
    0.66
     inherent
    0.65
    Activations Density 0.032%

    No Known Activations