© 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. 4-RES-JB
    11. 14630
    Prev
    Next
    INDEX
    Explanations

    mentions of where individuals live or are from

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "resident"

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

    No Comments

    Negative Logits
    anche
    -0.86
    displayText
    -0.82
    etheus
    -0.80
    enic
    -0.80
    arrell
    -0.79
    argon
    -0.78
    Bone
    -0.78
    reme
    -0.77
    anwhile
    -0.76
    matically
    -0.75
    POSITIVE LOGITS
    hips
    0.84
    ial
    0.77
     Evil
    0.77
     resident
    0.76
    ially
    0.76
    igi
    0.71
    Reviewer
    0.70
    iaries
    0.69
     occup
    0.69
    iate
    0.68
    Activations Density 0.010%

    No Known Activations