© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2688
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "People for the Ethical Treatment of Animals."

    oai_token-act-pair · gpt-3.5-turbo

    references to social or political groups and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.92
    enegger
    -0.74
    Success
    -0.74
    hent
    -0.70
     srfAttach
    -0.70
    Writer
    -0.69
    Pull
    -0.68
    è£ħ
    -0.68
    PORT
    -0.67
    Uncommon
    -0.67
    POSITIVE LOGITS
     whom
    0.71
     disabilities
    0.70
     balcon
    0.69
     confuse
    0.67
     grav
    0.66
    olia
    0.66
     hating
    0.66
     cov
    0.65
     starving
    0.65
    idia
    0.64
    Activations Density 0.303%

    No Known Activations