© 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. 9-RES-JB
    11. 3367
    Prev
    Next
    INDEX
    Explanations

    references to investigations, evidence, and conclusions related to criminal cases

    oai_token-act-pair · gpt-3.5-turbo

    indications of stolen items or fraudulent activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iberal
    -0.83
    oliberal
    -0.78
    enture
    -0.78
     dividend
    -0.74
     entrepreneurship
    -0.70
    productive
    -0.70
     advant
    -0.70
    adden
    -0.70
    galitarian
    -0.69
    agements
    -0.69
    POSITIVE LOGITS
     Forensic
    1.55
    Investigators
    1.51
     Investigators
    1.50
     investigators
    1.49
    Detect
    1.35
     forensic
    1.35
     detectives
    1.34
    nsic
    1.33
     Detect
    1.21
     investigator
    1.19
    Activations Density 0.743%

    No Known Activations