© 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. 18785
    Prev
    Next
    INDEX
    Explanations

    phrases related to police reports and crime scenes

    oai_token-act-pair · gpt-3.5-turbo

    statements made by police or authorities regarding incidents

    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
    TPP
    -0.89
    TABLE
    -0.77
    Ranked
    -0.76
    Quantity
    -0.74
    ãĥĩ
    -0.74
    HCR
    -0.74
    export
    -0.74
    Export
    -0.70
    Premium
    -0.69
    izont
    -0.69
    POSITIVE LOGITS
     they
    0.97
     detectives
    0.93
     investigators
    0.90
     witnesses
    0.89
     suspects
    0.84
     paramedics
    0.83
     suspect
    0.82
     probable
    0.82
     deputies
    0.81
     surveillance
    0.79
    Activations Density 0.131%

    No Known Activations