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. 1-RES-JB
    6. 14655
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning a wide variety or range of items

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "wide variety" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aminer
    -0.79
    LV
    -0.71
    CB
    -0.70
    MENT
    -0.63
    Lv
    -0.61
     Mineral
    -0.61
    lda
    -0.61
    irez
    -0.61
    igraph
    -0.60
    cair
    -0.60
    POSITIVE LOGITS
     wide
    1.10
     wider
    0.93
     breadth
    0.92
    leaf
    0.90
    sheets
    0.88
     variety
    0.88
     widened
    0.87
     spectrum
    0.86
     scope
    0.84
     range
    0.82
    Activations Density 0.011%

    No Known Activations