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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 7898
    Prev
    Next
    INDEX
    Explanations

    details related to crime scenes and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to criminal activities and associated events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    æ©Ł
    -0.60
     Expansion
    -0.59
    indust
    -0.56
    Improve
    -0.56
    DAQ
    -0.54
     revise
    -0.53
    erenn
    -0.53
     perenn
    -0.52
     Optim
    -0.52
    iets
    -0.52
    POSITIVE LOGITS
     stabbed
    1.23
     stabbing
    1.12
     robbery
    1.08
     robbers
    1.04
     gunman
    1.04
     gunned
    1.02
     murdered
    1.01
     fatally
    1.01
     abducted
    1.00
     raped
    0.99
    Activations Density 0.622%

    No Known Activations