© 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. 8-RES-JB
    11. 23467
    Prev
    Next
    INDEX
    Explanations

    technical terms related to equipment, machinery, services, and resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technical systems, specifically in industrial and domestic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĩãĤ£
    -0.55
    ãĥ´ãĤ¡
    -0.55
    itol
    -0.54
    ãĥ¼ãĥĨ
    -0.52
    riks
    -0.52
    Tweet
    -0.51
    oret
    -0.51
    ograp
    -0.50
    stice
    -0.50
    REF
    -0.50
    POSITIVE LOGITS
     respectively
    1.32
     alike
    0.81
     comprise
    0.74
    ↵↵
    0.71
    depending
    0.70
     abound
    0.67
    ¶
    0.66
     collide
    0.64
     converge
    0.64
     totaling
    0.63
    Activations Density 1.516%

    No Known Activations