© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17175
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing, such as comments, prescriptions, reviews, and books

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve writing or creating various types of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seekers
    -0.73
    ão
    -0.71
    ItemThumbnailImage
    -0.71
     granted
    -0.69
    hunter
    -0.66
     ownership
    -0.64
     claimants
    -0.63
     Persons
    -0.63
     hunters
    -0.62
     vantage
    -0.62
    POSITIVE LOGITS
     screenplay
    0.79
    itatively
    0.75
     diary
    0.71
     pulp
    0.70
     journal
    0.69
     aloud
    0.69
     journals
    0.67
     chapter
    0.66
     blog
    0.66
     autobiography
    0.66
    Activations Density 0.160%

    No Known Activations