© 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. 11667
    Prev
    Next
    INDEX
    Explanations

    references to academic studies or research

    oai_token-act-pair · gpt-3.5-turbo

    references to academic studies

    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
     sporting
    -0.75
     mill
    -0.72
     motors
    -0.69
     operating
    -0.69
     output
    -0.69
     amount
    -0.68
     channel
    -0.68
     cro
    -0.67
     gig
    -0.65
     pin
    -0.64
    POSITIVE LOGITS
     Study
    3.44
    Study
    2.21
     Studies
    1.55
    study
    1.49
     Examination
    1.30
     Survey
    1.29
     STUD
    1.24
    Studies
    1.24
     Discussion
    1.22
     Experiment
    1.20
    Activations Density 0.020%

    No Known Activations