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. 1-RES-JB
    6. 8436
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific experiments and research projects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical phenomena and scientific measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ched
    -0.72
     kitchens
    -0.64
    vati
    -0.64
    eve
    -0.63
     potency
    -0.63
    touch
    -0.60
     Kush
    -0.59
     Chin
    -0.59
     Khe
    -0.59
     priced
    -0.59
    POSITIVE LOGITS
    erm
    1.16
    uda
    1.03
    ilk
    0.96
    ont
    0.85
    andom
    0.84
    otor
    0.83
    obiles
    0.82
    agnetic
    0.79
    iot
    0.78
    obile
    0.77
    Activations Density 0.008%

    No Known Activations