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. 1451
    Prev
    Next
    INDEX
    Explanations

    safety and security-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security threats and illegal activities

    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
     sums
    -0.56
     CONTR
    -0.56
     Factors
    -0.55
     Balanced
    -0.53
     Donation
    -0.53
     Decision
    -0.52
     trust
    -0.51
    amen
    -0.51
     Piano
    -0.51
     gratitude
    -0.51
    POSITIVE LOGITS
     abound
    1.03
     prolifer
    0.98
     rampant
    0.98
     everywhere
    0.91
     popping
    0.91
     bloom
    0.89
     lurking
    0.84
     prevalent
    0.81
     emerge
    0.81
     thrive
    0.80
    Activations Density 1.348%

    No Known Activations