Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 3364
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a distinct or separate entity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Apart" and variations suggesting separation or distinction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IZE
    -0.78
     propagate
    -0.66
     crawl
    -0.62
     injure
    -0.61
     deposition
    -0.60
    Ç
    -0.60
     HRC
    -0.60
    083
    -0.60
    00000000
    -0.59
    vous
    -0.59
    POSITIVE LOGITS
    heid
    1.44
    comings
    1.23
    ments
    1.19
     Apart
    1.07
    osite
    0.93
    Apart
    0.82
    een
    0.76
    oslav
    0.75
    isphere
    0.75
    inguished
    0.74
    Activations Density 0.005%

    No Known Activations