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. 9-RES-JB
    6. 10435
    Prev
    Next
    INDEX
    Explanations

    actions involving handling, exchanging, or transferring items among individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and other related nouns and articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lectic
    -0.82
    ategory
    -0.81
    gae
    -0.81
    zai
    -0.81
    ħĭ
    -0.79
    ablishment
    -0.77
    galitarian
    -0.76
    venants
    -0.73
    wark
    -0.73
    onnaissance
    -0.72
    POSITIVE LOGITS
     entire
    1.25
     brunt
    1.22
     remainder
    1.22
     contents
    1.18
     ashes
    1.17
     belongings
    1.17
     remaining
    1.14
     leftover
    1.10
     entirety
    1.09
     offending
    1.08
    Activations Density 0.372%

    No Known Activations