© 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. 11-RES-JB
    11. 2649
    Prev
    Next
    INDEX
    Explanations

    technical terms related to various systems and processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology, systems, and tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redients
    -0.75
    NetMessage
    -0.72
    irens
    -0.71
    adies
    -0.69
    iths
    -0.68
    ãĥĥãĥī
    -0.68
    AppData
    -0.67
    ernels
    -0.67
     sqor
    -0.65
     Females
    -0.64
    POSITIVE LOGITS
     cannot
    1.26
     consists
    1.19
     might
    1.18
     can
    1.18
     tends
    1.16
     requires
    1.15
     could
    1.12
     would
    1.12
     may
    1.11
     exists
    1.11
    Activations Density 0.432%

    No Known Activations