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. 10-RES-JB
    6. 10885
    Prev
    Next
    INDEX
    Explanations

    numbers (including years) combined with words related to historical events

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and identifiers associated with statistics or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.64
    tering
    -0.62
    amac
    -0.61
    iman
    -0.58
    dict
    -0.56
    lins
    -0.56
    stration
    -0.56
     Situation
    -0.55
     brill
    -0.54
    mission
    -0.54
    POSITIVE LOGITS
    4
    1.71
    5
    1.67
    7
    1.66
    3
    1.66
    2
    1.61
    6
    1.57
    9
    1.52
    8
    1.51
    1
    1.43
    718
    1.16
    Activations Density 0.123%

    No Known Activations