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. 7549
    Prev
    Next
    INDEX
    Explanations

    adjectives related to degree or comparison

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that highlight varying degrees of significance or quality

    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
    stead
    -0.67
    ãĥİ
    -0.59
    SON
    -0.58
    ools
    -0.58
    ãĥīãĥ©ãĤ´ãĥ³
    -0.58
    Ws
    -0.56
    POR
    -0.56
    UCT
    -0.54
    inders
    -0.53
     MIN
    -0.52
    POSITIVE LOGITS
     athlet
    0.88
     anymore
    0.86
    idious
    0.84
     nor
    0.71
     as
    0.70
    amus
    0.70
    istic
    0.70
     defensively
    0.69
     than
    0.68
    itatively
    0.68
    Activations Density 0.114%

    No Known Activations