© 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. 6-RES-JB
    11. 11938
    Prev
    Next
    INDEX
    Explanations

    instances where entities make their first notable appearance or debut

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of possessive pronouns

    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
    hov
    -0.82
    earchers
    -0.64
     [];
    -0.61
    DN
    -0.60
    ibaba
    -0.59
    Guy
    -0.58
    Lago
    -0.57
    wr
    -0.56
     horizont
    -0.56
    Gi
    -0.56
    POSITIVE LOGITS
     own
    1.18
     debut
    0.88
     stride
    0.77
     impression
    0.77
    selves
    0.76
    self
    0.74
     footing
    0.73
     customary
    0.72
    çİĭ
    0.72
     displeasure
    0.70
    Activations Density 0.043%

    No Known Activations