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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 2979
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "blow the whistle," illustrating reporting wrongdoing or secrets

    oai_token-act-pair · gpt-3.5-turbo

    the term "whistle" in various contexts, particularly related to whistleblowers or whistle-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.77
    ggles
    -0.76
    itating
    -0.75
    arya
    -0.70
    ivia
    -0.69
    Ͻ
    -0.68
    itate
    -0.68
    itates
    -0.67
    itals
    -0.65
    alter
    -0.64
    POSITIVE LOGITS
     whistle
    1.25
     whist
    1.02
    dropping
    0.93
    keeper
    0.85
    pipe
    0.84
     sounded
    0.80
     blowing
    0.77
     blew
    0.77
    backs
    0.75
    bler
    0.75
    Activations Density 0.017%

    No Known Activations