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. 7497
    Prev
    Next
    INDEX
    Explanations

    technical terms and facts in the field of technology or economics

    oai_token-act-pair · gpt-3.5-turbo

    statements of fact pertaining to various subjects and characteristics

    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
     kisses
    -0.70
    lihood
    -0.60
     motions
    -0.60
    fight
    -0.59
    else
    -0.56
     Winn
    -0.56
     Anon
    -0.56
    ]."
    -0.55
    ]"
    -0.55
     Kardash
    -0.54
    POSITIVE LOGITS
    senal
    0.97
     remarkably
    0.88
     comprised
    0.87
     notoriously
    0.85
     depicted
    0.84
     strikingly
    0.83
     characterized
    0.81
     markedly
    0.76
     summarized
    0.75
     featured
    0.74
    Activations Density 0.599%

    No Known Activations