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. 10539
    Prev
    Next
    INDEX
    Explanations

    addresses and locations in text

    oai_token-act-pair · gpt-3.5-turbo

    key details about locations and events, often focusing on building names and significant actions

    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
     realise
    -0.83
    ?".
    -0.75
    !".
    -0.72
    avour
    -0.71
     organise
    -0.70
     organisation
    -0.67
     aluminium
    -0.66
     Whilst
    -0.66
     realised
    -0.65
    Firstly
    -0.65
    POSITIVE LOGITS
     Thursday
    1.20
     Monday
    1.19
     Wednesday
    1.18
     Tuesday
    1.17
     Friday
    1.14
     Saturday
    1.10
     beginning
    1.09
     tomorrow
    1.08
     Mondays
    1.07
     Sept
    1.03
    Activations Density 0.750%

    No Known Activations