Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9249
    Prev
    Next
    INDEX
    Explanations

    legal terms and references

    oai_token-act-pair · gpt-3.5-turbo

    references to personal possessions and their associated meanings or implications

    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
    opes
    -0.76
     Rates
    -0.73
    chers
    -0.71
     Modes
    -0.71
    udicrous
    -0.67
     regress
    -0.67
    atives
    -0.67
    isively
    -0.66
     refunds
    -0.66
    riers
    -0.65
    POSITIVE LOGITS
     or
    1.08
     preferably
    0.97
    someone
    0.92
     spouse
    0.88
    cknow
    0.85
    or
    0.80
    either
    0.79
     etc
    0.78
     appliance
    0.78
    etc
    0.77
    Activations Density 0.933%

    No Known Activations