Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 5374
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to people's names or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific character or individual represented by the symbol "Ļ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bloom
    -0.71
     elim
    -0.71
     mathemat
    -0.68
     convict
    -0.67
     cryst
    -0.65
     blender
    -0.64
     BCC
    -0.63
     Âł Âł Âł Âł
    -0.62
     pile
    -0.61
    raviolet
    -0.61
    POSITIVE LOGITS
    s
    1.09
    hood
    1.03
    ï¸ı
    0.94
    tre
    0.92
    sen
    0.91
    own
    0.90
    SHIP
    0.88
    ship
    0.85
    ski
    0.84
    tis
    0.83
    Activations Density 0.224%

    No Known Activations