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. 11-RES-JB
    6. 8233
    Prev
    Next
    INDEX
    Explanations

    mentions of military actions and historical events

    oai_token-act-pair · gpt-3.5-turbo

    professional and military context terms related to resource allocation and production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2013
    -1.18
    2014
    -1.14
     2014
    -1.10
     2013
    -1.09
    2015
    -1.08
     2015
    -1.08
    2017
    -1.07
    2012
    -1.05
     2017
    -1.04
    2011
    -1.04
    POSITIVE LOGITS
     Negro
    1.45
     railroad
    1.40
     postwar
    1.27
     wartime
    1.20
     typew
    1.19
    oslov
    1.19
     Roosevelt
    1.14
     1935
    1.12
     1934
    1.12
     Rockefeller
    1.11
    Activations Density 1.180%

    No Known Activations