© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 1934
    Prev
    Next
    INDEX
    Explanations

    terms related to considering options or making decisions, often involving comparisons or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of weighing or evaluating options and considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    href
    -0.72
    ellen
    -0.69
     Franç
    -0.67
    BLE
    -0.66
    EEE
    -0.66
     Scrib
    -0.66
    ilk
    -0.65
     Tul
    -0.65
     Nou
    -0.63
    activ
    -0.63
    POSITIVE LOGITS
     weigh
    1.44
     weighing
    1.17
    ighed
    1.14
     weighed
    1.06
     weighs
    1.02
     weights
    0.94
     corrid
    0.85
     scales
    0.84
    weights
    0.80
     cooker
    0.79
    Activations Density 0.008%

    No Known Activations