© 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. 2-RES-JB
    11. 3985
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'Titanium'

    oai_token-act-pair · gpt-3.5-turbo

    references to the material "titanium" and its various contexts

    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
    lishing
    -0.78
    rooms
    -0.75
    look
    -0.71
    testing
    -0.70
    ingly
    -0.69
    defined
    -0.69
    edly
    -0.68
    lisher
    -0.68
    stro
    -0.67
    names
    -0.67
    POSITIVE LOGITS
    Ti
    1.32
    Vo
    1.13
     Ti
    1.01
    oga
    0.92
    pler
    0.88
    obe
    0.84
    pered
    0.82
    ason
    0.79
    oxin
    0.78
    ango
    0.77
    Activations Density 0.007%

    No Known Activations