© 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. 4-RES-JB
    11. 10238
    Prev
    Next
    INDEX
    Explanations

    references to the airline company "Pan Am"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Pan American context, including organizations, events, and identifiers associated with it

    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
    gotten
    -0.67
    ACTED
    -0.63
    self
    -0.63
    FTWARE
    -0.63
     Argon
    -0.62
     surg
    -0.62
    VID
    -0.60
    owship
    -0.60
     impe
    -0.59
     spots
    -0.58
    POSITIVE LOGITS
    monary
    0.82
    sylvania
    0.77
    ued
    0.73
    insula
    0.70
    olate
    0.70
    auld
    0.69
    acs
    0.69
    uese
    0.68
    Indian
    0.68
    iflower
    0.68
    Activations Density 0.127%

    No Known Activations