© 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. 1-RES-JB
    11. 14504
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigative activities conducted by detectives or law enforcement officials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of investigators in a context related to ongoing inquiries or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rip
    -0.76
    south
    -0.66
    nu
    -0.64
    nic
    -0.63
    dos
    -0.62
     Birth
    -0.61
    lord
    -0.61
    corn
    -0.61
    tz
    -0.61
    ea
    -0.61
    POSITIVE LOGITS
     investigator
    1.17
     investigators
    1.14
     confir
    1.02
     Investigators
    1.02
     investigating
    0.96
     uncovered
    0.90
     investigation
    0.89
     GOODMAN
    0.88
     probing
    0.85
     conclud
    0.85
    Activations Density 0.016%

    No Known Activations