© 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. 10-RES-JB
    11. 10223
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activity and suspects

    oai_token-act-pair · gpt-3.5-turbo

    content related to criminal incidents and suspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anan
    -0.76
    ripp
    -0.76
    mbuds
    -0.75
     Glac
    -0.74
    utical
    -0.73
     maternity
    -0.73
    ¢
    -0.72
     childbirth
    -0.72
    issance
    -0.71
    agra
    -0.68
    POSITIVE LOGITS
    hunt
    1.16
     explosives
    1.16
     confessed
    1.12
     apprehended
    1.11
     detonated
    1.10
     deton
    1.07
     armed
    1.05
     motive
    1.02
     gunmen
    1.01
     disgu
    0.99
    Activations Density 0.553%

    No Known Activations