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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 98
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to the conclusion or completion of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the conclusion or finality of a situation

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

    the phrase "at the end"

    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
    htaking
    -0.82
    issance
    -0.78
    kaya
    -0.76
    æ©Ł
    -0.75
    pload
    -0.67
    thouse
    -0.67
    hee
    -0.66
    tyard
    -0.64
    esis
    -0.64
    BLIC
    -0.63
    POSITIVE LOGITS
    angering
    1.22
    owment
    1.17
    ocrine
    0.96
    ocrin
    0.93
    angers
    0.90
    door
    0.83
    orses
    0.82
    game
    0.81
    angered
    0.80
    orph
    0.74
    Activations Density 0.047%

    No Known Activations