© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 14774
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or places

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific group or community associated with the term "Pas."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.70
    ship
    -0.68
    ocating
    -0.66
    initions
    -0.65
    ickson
    -0.65
    ACTED
    -0.63
     wills
    -0.63
    ships
    -0.63
    itatively
    -0.62
    ĪĴ
    -0.62
    POSITIVE LOGITS
    sth
    1.22
    chal
    1.21
    chall
    0.97
    atell
    0.96
    ques
    0.94
    quet
    0.93
    nown
    0.92
     Pas
    0.88
     Pes
    0.84
    adena
    0.83
    Activations Density 0.012%

    No Known Activations