© 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 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. 7-RES-JB
    11. 1721
    Prev
    Next
    INDEX
    Explanations

    phrases related to detective work or police investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to detectives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -1.02
    jri
    -0.88
     Centauri
    -0.82
    bows
    -0.81
    eworld
    -0.81
     deaf
    -0.79
    kef
    -0.76
    rights
    -0.76
    enei
    -0.75
    accessible
    -0.75
    POSITIVE LOGITS
     Grimoire
    1.12
    ective
    0.93
     detective
    0.89
     Detective
    0.83
     Inspector
    0.81
     Constable
    0.79
     Sergeant
    0.78
     sergeant
    0.77
     Conan
    0.73
     detectives
    0.73
    Activations Density 0.051%

    No Known Activations