© 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. 561
    Prev
    Next
    INDEX
    Explanations

    references to the name "Dal" with various numbers appended to it

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Dal" in various contexts

    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
    axis
    -0.74
     Asheville
    -0.66
     promoter
    -0.64
    Pl
    -0.64
     promoters
    -0.63
    orbit
    -0.62
    plate
    -0.62
     jets
    -0.62
     Phelps
    -0.62
     modeling
    -0.61
    POSITIVE LOGITS
     Dal
    4.11
    dal
    1.48
     Lal
    1.33
     Dale
    1.28
     Bridgewater
    1.18
     Dum
    1.12
     Kal
    1.02
     Rath
    1.00
     Khal
    0.99
     Din
    0.99
    Activations Density 0.009%

    No Known Activations