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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 2-RES-JB
    6. 57
    Prev
    Next
    INDEX
    Explanations

    mentions of the start of something, like projects, events, or activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "began."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the past tense of the verb 'to begin'

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etry
    -0.75
    rats
    -0.72
    stood
    -0.71
    Zone
    -0.68
    acho
    -0.68
    road
    -0.67
    houses
    -0.67
    onomic
    -0.66
    versions
    -0.64
    allo
    -0.64
    POSITIVE LOGITS
     anew
    1.03
    NetMessage
    0.76
    OPLE
    0.73
    ŃĶ
    0.70
    wcs
    0.69
    ITIES
    0.68
     airing
    0.67
    Ò
    0.67
     attRot
    0.67
     withd
    0.67
    Activations Density 0.028%

    No Known Activations