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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 16473
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named Dornar

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Donnarumma."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ences
    -0.83
    ITNESS
    -0.76
    UID
    -0.76
     newsp
    -0.74
    perture
    -0.73
     UID
    -0.72
     AQ
    -0.72
    UCT
    -0.69
    ORGE
    -0.69
     UPS
    -0.69
    POSITIVE LOGITS
    nar
    1.13
    kees
    0.91
    sson
    0.89
    itic
    0.89
    stan
    0.88
    ashtra
    0.85
    ayan
    0.84
    izont
    0.83
    ussian
    0.82
    illion
    0.82
    Activations Density 0.004%

    No Known Activations