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. 10-RES-JB
    6. 14308
    Prev
    Next
    INDEX
    Explanations

    instances of the word "what" followed by a strong activation value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in what," indicating specific contexts or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orest
    -0.65
    entry
    -0.63
     Memor
    -0.59
    hig
    -0.59
    ocket
    -0.57
    oint
    -0.57
    achment
    -0.56
    ovo
    -0.56
    ridges
    -0.56
     guiActiveUnfocused
    -0.55
    POSITIVE LOGITS
     amounted
    1.04
     amounts
    1.00
     appears
    0.99
     organisers
    0.91
     transpired
    0.91
     seems
    0.89
     seemed
    0.86
     resembles
    0.84
     became
    0.84
     appeared
    0.84
    Activations Density 0.039%

    No Known Activations