© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6253
    Prev
    Next
    INDEX
    Explanations

    instances where something is required or necessary

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "needs."

    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
    numbered
    -0.66
    fashion
    -0.65
    laugh
    -0.63
    joining
    -0.63
    reverse
    -0.61
    uted
    -0.59
    quished
    -0.59
    upe
    -0.58
    np
    -0.57
    chard
    -0.57
    POSITIVE LOGITS
     needs
    3.52
     Needs
    2.90
    needs
    2.90
     need
    2.03
     NEED
    1.91
     wants
    1.74
     needed
    1.71
     demands
    1.59
     deserves
    1.57
     desires
    1.56
    Activations Density 0.026%

    No Known Activations