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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 18
    Prev
    Next
    INDEX
    Explanations

    instances of the word "afterwards" within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate subsequent actions or events

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

    the word "afterwards" or its variants

    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
    rod
    -0.69
    foot
    -0.68
    ASE
    -0.68
    yu
    -0.66
    icles
    -0.65
    hma
    -0.64
    =-=-=-=-=-=-=-=-
    -0.61
    axis
    -0.60
     Flavoring
    -0.59
    Especially
    -0.58
    POSITIVE LOGITS
    theless
    0.93
    etheless
    0.93
     afterwards
    0.89
     afterward
    0.89
    noon
    0.85
     satell
    0.82
     thereafter
    0.81
    vernment
    0.81
     conclud
    0.74
    eatures
    0.74
    Activations Density 0.006%

    No Known Activations