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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 21180
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names or terms associated with notable individuals, particularly in the entertainment or political sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.87
    âĶĢâĶĢ
    -0.84
     Cyprus
    -0.72
     Confederation
    -0.71
    ;;;;;;;;;;;;
    -0.70
     Georgian
    -0.68
    ÄŁ
    -0.68
    éĹĺ
    -0.66
     Azerbai
    -0.66
     Typhoon
    -0.65
    POSITIVE LOGITS
    lett
    0.81
    heny
    0.80
    xon
    0.76
    aney
    0.72
    zinski
    0.71
    hey
    0.70
    antz
    0.70
    zik
    0.69
    bett
    0.68
    bish
    0.68
    Activations Density 0.186%

    No Known Activations