© 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. 22414
    Prev
    Next
    INDEX
    Explanations

    the name "Neuron" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "Ne" 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
    wrapper
    -0.72
     gar
    -0.72
    obar
    -0.66
    heed
    -0.65
     Jackie
    -0.65
    skirts
    -0.64
     ordinances
    -0.63
    bucks
    -0.63
    dash
    -0.63
    ATHER
    -0.63
    POSITIVE LOGITS
     Ne
    3.52
    Ne
    2.56
     ne
    1.78
     Neo
    1.74
     Neh
    1.45
     NE
    1.45
    ne
    1.32
     Neb
    1.24
     neur
    1.23
     Mes
    1.22
    Activations Density 0.020%

    No Known Activations