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. 224
    Prev
    Next
    INDEX
    Explanations

    metaphorical expressions or analogies describing transformation and progression

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transformation and growth

    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
    )."
    -0.77
    ]."
    -0.74
     accordingly
    -0.68
     anyways
    -0.67
    )).
    -0.65
     beforehand
    -0.64
    RESULTS
    -0.64
     anyway
    -0.63
    Otherwise
    -0.61
    Closure
    -0.58
    POSITIVE LOGITS
     thy
    0.55
    htaking
    0.54
     typew
    0.53
     Nobel
    0.52
    ursday
    0.51
     chimpan
    0.50
     hamm
    0.50
    razil
    0.47
     polio
    0.47
     Thanksgiving
    0.46
    Activations Density 1.657%

    No Known Activations