© 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. 4-RES-JB
    11. 10713
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to phones or technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term related to "phishing."

    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
    éĹĺ
    -1.20
    HCR
    -0.81
    ndra
    -0.79
    ACTED
    -0.75
    PRES
    -0.73
     Recovery
    -0.71
    ãĤ¤ãĥĪ
    -0.71
    CLASSIFIED
    -0.70
    Interstitial
    -0.68
    ãĥ¼ãĤ¯
    -0.66
    POSITIVE LOGITS
    oenix
    1.26
    araoh
    1.12
    antom
    1.11
    yll
    1.06
    ilipp
    1.05
    izoph
    1.04
    osp
    1.03
    ipp
    1.01
    obia
    1.00
    iod
    0.99
    Activations Density 0.008%

    No Known Activations