© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18715
    Prev
    Next
    INDEX
    Explanations

    scientific research references

    oai_token-act-pair · gpt-3.5-turbo

    references and citation information from scientific documents

    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
     evict
    -0.75
     decre
    -0.74
     cruiser
    -0.72
     piping
    -0.70
     inspecting
    -0.69
     destro
    -0.69
     renting
    -0.69
     whim
    -0.68
     gent
    -0.67
     vigilante
    -0.67
    POSITIVE LOGITS
    doi
    1.67
    Abstract
    1.64
     DOI
    1.59
     doi
    1.46
    Explore
    1.29
     Neuroscience
    1.23
     Abstract
    1.23
    Nature
    1.23
    Phys
    1.21
     dx
    1.16
    Activations Density 0.209%

    No Known Activations