© 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. 6-RES-JB
    11. 18455
    Prev
    Next
    INDEX
    Explanations

    phrases related to separation or ending relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to separation or parting situations

    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
    DonaldTrump
    -0.75
    trak
    -0.74
    ECH
    -0.73
    TRY
    -0.72
    gravity
    -0.71
    eq
    -0.71
    eers
    -0.70
    KT
    -0.69
    arios
    -0.68
    arya
    -0.67
    POSITIVE LOGITS
     parting
    0.93
     parted
    0.92
     sep
    0.75
    atform
    0.73
     hairs
    0.71
     plat
    0.70
    uary
    0.69
     farewell
    0.68
    lass
    0.68
     sever
    0.68
    Activations Density 0.035%

    No Known Activations