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. 8379
    Prev
    Next
    INDEX
    Explanations

    verbs indicating strong emotions or personal perspectives

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various tenses

    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
     Previous
    -0.54
    inav
    -0.54
    atives
    -0.53
     Which
    -0.51
     Benefits
    -0.51
    stop
    -0.51
    urry
    -0.49
     IMAGES
    -0.49
     Moines
    -0.48
    osate
    -0.47
    POSITIVE LOGITS
    nt
    0.89
     supposed
    0.83
     definitely
    0.78
    senal
    0.77
     not
    0.73
     indeed
    0.72
     unlikely
    0.71
    rael
    0.71
     always
    0.71
     able
    0.71
    Activations Density 0.830%

    No Known Activations