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. 7-RES-JB
    6. 1007
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to news articles or current events

    oai_token-act-pair · gpt-3.5-turbo

    the word "has" in various contexts, often indicating possession or actions taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eem
    -0.77
    etting
    -0.68
     behold
    -0.66
    most
    -0.63
    seless
    -0.63
    oppable
    -0.61
    RFC
    -0.61
    anny
    -0.59
    ecd
    -0.59
    inkle
    -0.58
    POSITIVE LOGITS
     been
    1.38
    been
    1.16
     undergone
    1.10
     become
    1.09
     emerged
    1.05
     begun
    1.02
     apologised
    1.00
     arisen
    0.93
     learnt
    0.92
     risen
    0.90
    Activations Density 0.253%

    No Known Activations