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. 1533
    Prev
    Next
    INDEX
    Explanations

    keywords related to discarding or disposing of things, such as 'dump'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dump" in various contexts

    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
    Reviewed
    -0.81
    HCR
    -0.81
    ghai
    -0.70
    avery
    -0.70
    MSN
    -0.69
    iam
    -0.66
     Realms
    -0.66
     Lear
    -0.64
    velength
    -0.62
     Flavoring
    -0.61
    POSITIVE LOGITS
     dumps
    1.14
    dump
    1.11
    ster
    0.97
    loads
    0.91
    sters
    0.89
     dump
    0.87
     dumping
    0.79
     heap
    0.79
    tor
    0.78
    liga
    0.75
    Activations Density 0.018%

    No Known Activations