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. 10-RES-JB
    6. 3849
    Prev
    Next
    INDEX
    Explanations

    sophisticated and complex terms related to language and ideology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rhetoric and theoretical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etts
    -0.84
    igun
    -0.80
    cot
    -0.73
     looted
    -0.72
    rb
    -0.71
    lain
    -0.71
    icular
    -0.70
     commercially
    -0.70
    Corp
    -0.70
    edin
    -0.70
    POSITIVE LOGITS
     impossibility
    1.14
     superiority
    1.08
     underpin
    1.04
     certainty
    1.04
     sophistication
    1.02
     equival
    0.98
     inconsistency
    0.97
     reasoning
    0.95
     grounding
    0.94
     justification
    0.92
    Activations Density 0.119%

    No Known Activations