© 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. 9-RES-JB
    11. 18600
    Prev
    Next
    INDEX
    Explanations

    mentions of specific occupations or roles within a community

    oai_token-act-pair · gpt-3.5-turbo

    references to community dynamics and personal anecdotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pires
    -0.77
    pmwiki
    -0.66
    toggle
    -0.65
    ":{"
    -0.63
    )?
    -0.62
    ?ãĢį
    -0.62
    ãĥīãĥ©
    -0.62
    Enlarge
    -0.61
     VICE
    -0.59
    Flickr
    -0.57
    POSITIVE LOGITS
     whilst
    1.38
     whereas
    1.21
     but
    1.12
     although
    1.06
     however
    1.05
     whereby
    1.05
     because
    1.03
     which
    0.98
     stating
    0.95
     though
    0.94
    Activations Density 1.420%

    No Known Activations