© 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. 10264
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or concepts of interest

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and assess their prevalence

    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
    Discuss
    -0.77
    bj
    -0.75
    agues
    -0.74
    sburg
    -0.72
    buster
    -0.71
    Default
    -0.71
    Goal
    -0.69
    thood
    -0.68
    ndum
    -0.68
    wark
    -0.67
    POSITIVE LOGITS
     fact
    1.86
     sheer
    1.39
     amount
    1.27
     way
    1.24
     plethora
    1.19
     absence
    1.16
     multitude
    1.15
     abundance
    1.15
     extent
    1.11
     manner
    1.10
    Activations Density 0.304%

    No Known Activations