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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 3759
    Prev
    Next
    INDEX
    Explanations

    two-word phrases that begin with "I came" or "I come", possibly indicating personal experiences or realizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the act of coming to a conclusion or realization

    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
    IELD
    -0.71
    orsche
    -0.65
    reality
    -0.60
    bush
    -0.59
    bon
    -0.59
    esson
    -0.58
    hawks
    -0.57
    tten
    -0.56
    Discuss
    -0.56
    eele
    -0.56
    POSITIVE LOGITS
     undone
    0.89
     hither
    0.85
     across
    0.79
     unst
    0.75
    ĸļ
    0.67
    ued
    0.67
    backs
    0.67
     face
    0.66
    actionDate
    0.65
     peril
    0.64
    Activations Density 0.063%

    No Known Activations