© 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. 0-RES-JB
    11. 8132
    Prev
    Next
    INDEX
    Explanations

    references to specific volumes or issues of something

    oai_token-act-pair · gpt-3.5-turbo

    references to volumes or issues in a series, particularly relating to "Vol" and certain terms associated with crises and help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stellar
    -0.72
     Alam
    -0.69
     boosters
    -0.68
     Shield
    -0.67
     opener
    -0.63
     Mason
    -0.63
     Acad
    -0.63
     Elite
    -0.63
     congratulations
    -0.63
     partisans
    -0.62
    POSITIVE LOGITS
    Vol
    2.63
    Street
    1.47
    Help
    1.41
    Fight
    1.37
    Write
    1.26
    Toy
    1.26
    Job
    1.24
    VW
    1.20
    Oil
    1.17
     depths
    1.14
    Activations Density 0.036%

    No Known Activations