© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3554
    Prev
    Next
    INDEX
    Explanations

    information related to providing medical assistance and support services for communities in need

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    services and support related to healthcare and community assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raq
    -0.88
    ername
    -0.88
    PLA
    -0.84
    roth
    -0.81
    bryce
    -0.80
    eki
    -0.80
    anamo
    -0.80
    asc
    -0.78
    dash
    -0.76
    eny
    -0.75
    POSITIVE LOGITS
     counseling
    1.23
     counselling
    1.22
     assistance
    1.17
     referrals
    1.16
     prenatal
    1.13
     care
    1.13
     medication
    1.07
     services
    1.06
     nutritious
    1.06
     vocational
    1.05
    Activations Density 0.244%

    No Known Activations