Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11883
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "hope"

    oai_token-act-pair · gpt-3.5-turbo

    words that contain the substring "ope"

    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
    dimension
    -0.75
    Issue
    -0.72
    century
    -0.70
    skill
    -0.70
    invoke
    -0.68
    ItemImage
    -0.66
    INTON
    -0.66
    minded
    -0.65
    ivan
    -0.64
    EVA
    -0.63
    POSITIVE LOGITS
    ope
    1.27
    opes
    0.86
    odies
    0.74
    OPE
    0.71
    ace
    0.70
    olic
    0.69
    atives
    0.69
    atively
    0.68
    OPLE
    0.68
    olics
    0.68
    Activations Density 0.006%

    No Known Activations