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. 251
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is expressing personal thoughts or actions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to communication and interaction

    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
    ratulations
    -0.77
     unlaw
    -0.71
    locks
    -0.71
     Dot
    -0.65
    lock
    -0.64
    gress
    -0.64
    grave
    -0.59
    Sov
    -0.59
    JUST
    -0.59
    lyak
    -0.57
    POSITIVE LOGITS
    adelphia
    0.83
    ometimes
    0.81
    ginx
    0.77
    advertisement
    0.75
     yearly
    0.73
    pmwiki
    0.69
    ided
    0.69
    veland
    0.69
     Gleaming
    0.66
     weekly
    0.65
    Activations Density 0.912%

    No Known Activations