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. 11-RES-JB
    6. 3287
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions or processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of notable educational or institutional changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.71
    opes
    -0.66
    eteen
    -0.65
    uitive
    -0.64
    Details
    -0.63
    ocamp
    -0.62
    amiliar
    -0.62
     nonetheless
    -0.61
     certainty
    -0.60
    ixty
    -0.59
    POSITIVE LOGITS
     negatively
    1.17
     unfairly
    1.13
     adversely
    1.12
     discriminated
    1.08
     infring
    1.06
     harmed
    1.05
     plagiar
    1.04
     deval
    1.04
     sabot
    1.03
     detrimental
    1.02
    Activations Density 0.623%

    No Known Activations