© 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. 0-RES-JB
    11. 22712
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or terms

    oai_token-act-pair · gpt-3.5-turbo

    the word "tha" and related variations, indicating a focus on conjunctions or connecting phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     macros
    -0.64
     executive
    -0.64
     independent
    -0.64
     warrants
    -0.63
     budgets
    -0.63
     pixel
    -0.62
     compensation
    -0.62
     macro
    -0.62
     exclusive
    -0.60
     acquisition
    -0.60
    POSITIVE LOGITS
    tha
    4.69
    thia
    1.59
    thal
    1.51
    thy
    1.37
    th
    1.32
    thur
    1.19
    than
    1.19
    thel
    1.19
    ths
    1.18
    atha
    1.10
    Activations Density 0.019%

    No Known Activations