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. 20589
    Prev
    Next
    INDEX
    Explanations

    information related to events like accidents, incidents, arrests, and reports

    oai_token-act-pair · gpt-3.5-turbo

    comma-separated phrases or lists

    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
    sylv
    -0.70
     Millenn
    -0.65
     FOIA
    -0.65
     awhile
    -0.65
    NetMessage
    -0.64
     instructional
    -0.63
    !--
    -0.62
    :(
    -0.61
     realization
    -0.60
    ggles
    -0.59
    POSITIVE LOGITS
     organisers
    0.99
     whilst
    0.95
     although
    0.92
     albeit
    0.92
     namely
    0.90
     according
    0.90
     Fifa
    0.89
     Notting
    0.89
     Defence
    0.87
    Scotland
    0.85
    Activations Density 0.733%

    No Known Activations