© 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. 1-RES-JB
    11. 16362
    Prev
    Next
    INDEX
    Explanations

    words related to austere environments and terms related to custody

    oai_token-act-pair · gpt-3.5-turbo

    words related to austere conditions and custody issues

    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
    culosis
    -0.98
     Sabha
    -0.84
    SHIP
    -0.82
    DragonMagazine
    -0.82
     Annotations
    -0.81
    Http
    -0.78
    FN
    -0.77
    QUEST
    -0.75
    FP
    -0.73
    Du
    -0.72
    POSITIVE LOGITS
     aust
    0.98
     mart
    0.94
     cust
    0.83
     cher
    0.76
     pers
    0.75
     custod
    0.74
    inas
    0.74
    gary
    0.73
     ess
    0.71
    ¨
    0.70
    Activations Density 0.020%

    No Known Activations