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. 3406
    Prev
    Next
    INDEX
    Explanations

    words related to necessity and difficulty, particularly in exchanges or reciprocation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the necessity and implications of societal structures and systems

    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
    icipated
    -0.76
    76561
    -0.70
     Cosponsors
    -0.69
    saw
    -0.66
     Entered
    -0.62
    herry
    -0.60
    edIn
    -0.60
     Sins
    -0.60
    idth
    -0.59
    uese
    -0.58
    POSITIVE LOGITS
     easier
    1.24
     obsolete
    1.17
     impossible
    1.17
     safer
    1.14
     redundant
    1.13
     impractical
    1.08
     unus
    1.08
     irrelevant
    1.05
     moot
    1.04
     inaccessible
    1.02
    Activations Density 0.137%

    No Known Activations