© 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. 10-RES-JB
    11. 17351
    Prev
    Next
    INDEX
    Explanations

    phrases related to clusters or groupings of things

    oai_token-act-pair · gpt-3.5-turbo

    references to clusters or groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OSP
    -0.74
    inez
    -0.66
     endors
    -0.65
    lvl
    -0.65
    +++
    -0.64
    Honest
    -0.62
    undai
    -0.59
    writers
    -0.59
     Thro
    -0.59
    CV
    -0.58
    POSITIVE LOGITS
    fuck
    1.11
     bom
    0.95
     clustered
    0.94
    alid
    0.82
     thereof
    0.81
    hedral
    0.80
    icles
    0.79
    inous
    0.78
     together
    0.77
     scattered
    0.76
    Activations Density 0.149%

    No Known Activations