© 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. 8-RES-JB
    11. 14126
    Prev
    Next
    INDEX
    Explanations

    descriptions of individuals who are reported missing

    oai_token-act-pair · gpt-3.5-turbo

    information related to missing persons reports

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     awarding
    -0.96
     Equal
    -0.82
     semif
    -0.75
     superiority
    -0.75
     applaud
    -0.74
     quotas
    -0.73
     empowering
    -0.72
     disadvantage
    -0.71
     faire
    -0.71
     unfair
    -0.71
    POSITIVE LOGITS
     whereabouts
    1.40
     vanished
    1.27
     disappeared
    1.24
     disappearance
    1.23
     sightings
    1.23
     mysteriously
    1.04
     abducted
    1.04
    odiac
    1.00
    nown
    0.99
     disappear
    0.98
    Activations Density 0.841%

    No Known Activations