Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 23416
    Prev
    Next
    INDEX
    Explanations

    words related to proximity or spatial location

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "around."

    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
    acity
    -0.67
    gression
    -0.63
    Direct
    -0.62
    ente
    -0.61
    onel
    -0.60
    Complete
    -0.60
    ITION
    -0.59
    Published
    -0.59
    ority
    -0.58
    answer
    -0.57
    POSITIVE LOGITS
     around
    3.31
    around
    2.37
     Around
    2.21
    Around
    1.99
     surrounding
    1.33
     across
    1.26
     round
    1.20
     anywhere
    1.16
     surrounds
    1.12
     everywhere
    1.12
    Activations Density 0.052%

    No Known Activations