© 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. 4-RES-JB
    11. 8662
    Prev
    Next
    INDEX
    Explanations

    terms related to real-time technology and data processing

    oai_token-act-pair · gpt-3.5-turbo

    references to "real-time" concepts or technologies

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

    No Comments

    Negative Logits
    urat
    -0.81
    ramid
    -0.80
    redit
    -0.80
    lain
    -0.79
    ieties
    -0.78
    udeb
    -0.76
    quet
    -0.76
    ategories
    -0.76
    iverpool
    -0.74
    erto
    -0.74
    POSITIVE LOGITS
     accuracy
    0.86
     inacc
    0.80
     analytics
    0.76
     accurate
    0.73
     monitoring
    0.73
     PCR
    0.72
    frames
    0.71
    aneously
    0.71
     executions
    0.71
     TTL
    0.70
    Activations Density 0.016%

    No Known Activations