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. 4-RES-JB
    6. 21861
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or end of a previous state of affairs

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "no longer" in various contexts indicating a change or discontinuation

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

    No Comments

    Negative Logits
     Enhancement
    -0.78
     Colour
    -0.75
    MAT
    -0.70
     Azure
    -0.69
    Enlarge
    -0.68
    é¾
    -0.67
    Stars
    -0.66
    imov
    -0.66
     Pan
    -0.65
    eers
    -0.64
    POSITIVE LOGITS
     extant
    0.82
     tolerated
    0.82
     obsolete
    0.80
     exist
    0.79
     exists
    0.79
     tolerate
    0.78
    theless
    0.76
     wedd
    0.72
    adays
    0.72
     hiber
    0.71
    Activations Density 0.013%

    No Known Activations