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. 6-RES-JB
    6. 1374
    Prev
    Next
    INDEX
    Explanations

    metaphors and similes comparing different situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    similes and metaphors that compare experiences to physical actions or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    formance
    -0.76
    etheless
    -0.75
     Judicial
    -0.71
    idates
    -0.70
    ©¶æ
    -0.67
    Support
    -0.66
    cipled
    -0.66
    RM
    -0.65
    tions
    -0.63
     Generations
    -0.63
    POSITIVE LOGITS
     Gest
    0.84
     Mole
    0.72
     doll
    0.71
     magnet
    0.71
     candy
    0.70
     pillow
    0.68
     downhill
    0.67
     steroids
    0.67
     miniature
    0.66
     mole
    0.63
    Activations Density 0.615%

    No Known Activations