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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9743
    Prev
    Next
    INDEX
    Explanations

    technical specifications and numeric details, potentially related to computer hardware

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to specifications or metrics

    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
     tremend
    -0.95
     pse
    -0.82
     corrid
    -0.75
     destro
    -0.75
    anim
    -0.73
    liction
    -0.72
     eleph
    -0.71
    soDeliveryDate
    -0.71
     proble
    -0.71
     carbohyd
    -0.71
    POSITIVE LOGITS
     Total
    1.22
     Difference
    1.21
     Miscellaneous
    1.16
     TOTAL
    1.16
     Unsure
    1.15
     Maximum
    1.13
     Unlimited
    1.13
     Conclusion
    1.12
     Average
    1.12
     Percentage
    1.12
    Activations Density 0.076%

    No Known Activations