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. 12127
    Prev
    Next
    INDEX
    Explanations

    financial figures expressed in billions or millions of dollars

    oai_token-act-pair · gpt-3.5-turbo

    numeric values representing monetary amounts

    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
    akeru
    -0.59
     grounding
    -0.58
     Wid
    -0.57
     Cod
    -0.56
     Blackwell
    -0.55
     Clifford
    -0.54
     Stef
    -0.54
     Rangers
    -0.54
    ufact
    -0.53
     Bleach
    -0.53
    POSITIVE LOGITS
     billion
    1.12
     Billion
    1.09
    -$
    1.09
    billion
    1.08
     million
    1.07
    million
    1.05
     trillion
    0.99
    120
    0.93
    000000
    0.91
    bn
    0.90
    Activations Density 0.075%

    No Known Activations