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. 8-RES-JB
    6. 5576
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and settlements

    oai_token-act-pair · gpt-3.5-turbo

    prepositional phrases indicating specific conditions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )|
    -0.63
    }}}
    -0.62
     *)
    -0.62
    })
    -0.61
    ...)
    -0.60
    âĢķ
    -0.60
    )}
    -0.60
    66666666
    -0.60
     (),
    -0.60
    ,[
    -0.58
    POSITIVE LOGITS
    etheless
    1.04
    umber
    0.71
    ntil
    0.66
    asty
    0.65
    avis
    0.63
    atever
    0.63
    ategory
    0.62
     whichever
    0.61
    utory
    0.61
    lished
    0.61
    Activations Density 0.474%

    No Known Activations