© 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. 1-RES-JB
    11. 20143
    Prev
    Next
    INDEX
    Explanations

    references to capabilities or limits

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "capacity."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nee
    -0.80
    rom
    -0.77
    dash
    -0.75
    pper
    -0.72
    aro
    -0.69
     Atari
    -0.69
    roma
    -0.69
    ochet
    -0.66
    enegger
    -0.64
    dal
    -0.63
    POSITIVE LOGITS
     capacity
    1.59
     capacities
    1.55
     Capacity
    1.29
    capacity
    1.09
    ibilities
    1.00
     utilization
    0.90
    idth
    0.88
     overflow
    0.80
    iencies
    0.80
     faculties
    0.79
    Activations Density 0.011%

    No Known Activations