© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 23990
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical places and people

    oai_token-act-pair · gpt-3.5-turbo

    names of authors or artists associated with various works, likely in a cultural or entertainment context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oneself
    -0.64
    theless
    -0.64
     confidential
    -0.62
     complicit
    -0.62
     pleas
    -0.59
     pertinent
    -0.58
     accordingly
    -0.57
     altogether
    -0.57
     yourself
    -0.56
    PDATE
    -0.56
    POSITIVE LOGITS
     âĵĺ
    1.05
    itars
    0.92
    astery
    0.89
     (?,
    0.72
    uctions
    0.72
    agogue
    0.71
     Profile
    0.70
    tones
    0.70
    insula
    0.69
    iatus
    0.67
    Activations Density 0.570%

    No Known Activations