Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17
    Prev
    Next
    INDEX
    Explanations

    elements or descriptions related to the sensory feel or atmosphere of something

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of emotions and aesthetic qualities associated with various experiences

    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
     Articles
    -0.66
    onga
    -0.62
     papers
    -0.61
     Tracker
    -0.61
     Hay
    -0.60
     Journals
    -0.60
     Diagn
    -0.60
     cages
    -0.59
    isc
    -0.59
     PET
    -0.59
    POSITIVE LOGITS
    tones
    1.07
    iness
    1.04
     reminiscent
    0.96
    fulness
    0.93
    smanship
    0.93
     belie
    0.92
     perv
    0.92
    lessness
    0.91
    abl
    0.89
     vibe
    0.88
    Activations Density 0.329%

    No Known Activations