© 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. 0-RES-JB
    6. 17018
    Prev
    Next
    INDEX
    Explanations

    specific or designated items or values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "specified" in various contexts

    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
     cherish
    -0.80
     underestimate
    -0.77
    ettle
    -0.75
    answer
    -0.75
    agy
    -0.71
    amac
    -0.71
     VIDEOS
    -0.70
    undrum
    -0.70
    ulia
    -0.68
     resonate
    -0.68
    POSITIVE LOGITS
     specified
    2.87
     prescribed
    1.98
     mandated
    1.86
     imposed
    1.66
    specified
    1.59
     regulated
    1.52
     designated
    1.49
     defined
    1.48
     allotted
    1.44
     requested
    1.40
    Activations Density 0.020%

    No Known Activations