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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 14621
    Prev
    Next
    INDEX
    Explanations

    phrases related to memories or recollections

    oai_token-act-pair · gpt-3.5-turbo

    memories or recollections of past experiences

    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
     accommodation
    -0.65
     OPT
    -0.62
     strengthening
    -0.60
    ¶
    -0.58
     harms
    -0.58
    ependent
    -0.56
     weakening
    -0.56
     urgently
    -0.54
     enrich
    -0.54
    wage
    -0.54
    POSITIVE LOGITS
     uttered
    0.90
    laughs
    0.70
     nickname
    0.68
     chuckled
    0.67
     perished
    0.66
    Laughs
    0.65
     exclaimed
    0.65
     wore
    0.65
     coined
    0.65
     moniker
    0.64
    Activations Density 1.648%

    No Known Activations