© 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. 22794
    Prev
    Next
    INDEX
    Explanations

    locations or positions denoted by the word "Near."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Near" 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
     duty
    -0.62
    rix
    -0.62
    onda
    -0.60
     resign
    -0.59
     resignation
    -0.59
    ek
    -0.58
     action
    -0.58
     apologise
    -0.58
     anthem
    -0.58
    orial
    -0.58
    POSITIVE LOGITS
     Near
    3.93
    Near
    2.65
    near
    2.06
     near
    1.25
    Neigh
    1.06
     Middle
    1.04
     Neigh
    1.02
     Close
    1.01
     Indo
    1.00
     Else
    1.00
    Activations Density 0.015%

    No Known Activations