© 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. 3-RES-JB
    11. 13583
    Prev
    Next
    INDEX
    Explanations

    the name "Troy" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Troy" and its associated variations or mentions in different contexts

    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
    unknown
    -0.87
    overs
    -0.77
    pmwiki
    -0.76
    cffffcc
    -0.75
    ISTER
    -0.72
    ña
    -0.71
    backer
    -0.71
    Downloadha
    -0.69
    女
    -0.65
     supervised
    -0.64
    POSITIVE LOGITS
     Troy
    0.91
    anus
    0.85
    ©¶æ¥µ
    0.81
    anium
    0.81
    ometry
    0.75
     Tul
    0.75
    lock
    0.74
     Trace
    0.72
    ility
    0.71
     Parish
    0.70
    Activations Density 0.006%

    No Known Activations