© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11655
    Prev
    Next
    INDEX
    Explanations

    pronouns and spatial relation words associated with people or objects behind the subject

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and groups in different contexts, particularly positions relative to 'him,' 'them,' and 'us.'

    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
     Compliance
    -0.70
     Podesta
    -0.68
     HRC
    -0.66
     Membership
    -0.65
     Heist
    -0.62
     fact
    -0.62
     Meaning
    -0.60
    yout
    -0.60
    oxy
    -0.60
    itialized
    -0.60
    POSITIVE LOGITS
    adows
    0.78
     trembling
    0.69
     eman
    0.67
     crumbling
    0.66
     crumble
    0.65
    atic
    0.65
     blurred
    0.65
    alian
    0.64
    ulkan
    0.64
    self
    0.64
    Activations Density 0.112%

    No Known Activations