© 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. 2-RES-JB
    11. 24035
    Prev
    Next
    INDEX
    Explanations

    mentions of capacity in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "capacity" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rom
    -0.71
    ochet
    -0.69
    aro
    -0.69
    dash
    -0.67
    pper
    -0.66
    enegger
    -0.65
    generic
    -0.65
    roma
    -0.64
     Kubrick
    -0.64
     Atari
    -0.64
    POSITIVE LOGITS
     capacities
    1.42
     capacity
    1.42
     Capacity
    1.17
    ibilities
    1.04
    capacity
    0.96
     utilization
    0.95
    auga
    0.78
     faculties
    0.77
    iencies
    0.77
     overflow
    0.76
    Activations Density 0.012%

    No Known Activations