© 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. 4-RES-JB
    11. 9329
    Prev
    Next
    INDEX
    Explanations

    language related to police investigations and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    themes related to moral dilemmas and deception

    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
     Pwr
    -0.56
    oji
    -0.50
    sembly
    -0.50
    ractions
    -0.47
    ikarp
    -0.47
    ramid
    -0.46
    fecture
    -0.46
    heast
    -0.46
    OPS
    -0.45
    soon
    -0.45
    POSITIVE LOGITS
     nihil
    0.66
     epist
    0.66
    ingly
    0.60
     moral
    0.59
     philosoph
    0.59
     existential
    0.57
     empir
    0.57
     caus
    0.57
    itarian
    0.56
     insofar
    0.56
    Activations Density 1.707%

    No Known Activations