© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 3294
    Prev
    Next
    INDEX
    Explanations

    references to military personnel, particularly soldiers

    oai_token-act-pair · gpt-3.5-turbo

    references to military personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TERN
    -0.94
    omial
    -0.76
    âĶĢâĶĢâĶĢâĶĢ
    -0.75
     Pwr
    -0.75
    Solution
    -0.75
    CAST
    -0.74
    FORMATION
    -0.66
    tera
    -0.66
     Vul
    -0.65
    poses
    -0.65
    POSITIVE LOGITS
     stationed
    1.14
     fatig
    0.91
     uniforms
    0.90
     barracks
    0.84
     soldiers
    0.83
     reserv
    0.80
     garrison
    0.80
     acad
    0.78
     salute
    0.78
     deployed
    0.78
    Activations Density 0.016%

    No Known Activations