© 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. 8-RES-JB
    11. 319
    Prev
    Next
    INDEX
    Explanations

    words related to feelings or sensations, particularly those related to a nostalgic or retro aesthetic

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to nostalgic or retro qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Articles
    -0.71
     PowerPoint
    -0.66
     papers
    -0.66
     copies
    -0.65
     aborted
    -0.61
     Journals
    -0.61
    USS
    -0.61
     timet
    -0.61
     paperwork
    -0.59
     WATCHED
    -0.59
    POSITIVE LOGITS
    tones
    1.18
    iness
    1.17
     perv
    1.08
    lessness
    1.01
    iqueness
    0.96
    fulness
    0.95
     vibe
    0.93
    terness
    0.91
    abl
    0.91
     aura
    0.89
    Activations Density 0.323%

    No Known Activations