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. 0-RES-JB
    6. 19841
    Prev
    Next
    INDEX
    Explanations

    prices and numerical values in various online listings

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values and pricing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lings
    -0.75
     association
    -0.68
    ling
    -0.66
     shake
    -0.65
     gymn
    -0.63
    ographers
    -0.62
     Bard
    -0.61
     applause
    -0.61
     cycling
    -0.61
     burst
    -0.60
    POSITIVE LOGITS
    99
    3.48
    97
    2.18
    98
    2.15
    95
    2.07
    999
    2.05
    96
    1.93
    995
    1.88
    998
    1.86
    94
    1.84
    93
    1.84
    Activations Density 0.022%

    No Known Activations