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. 7-RES-JB
    6. 12942
    Prev
    Next
    INDEX
    Explanations

    phrases where something happens despite unfavorable circumstances

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating resilience or persistence in the face of adversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irements
    -0.75
     encyclopedia
    -0.74
     NCT
    -0.65
     oats
    -0.62
     groceries
    -0.62
     Goff
    -0.61
    Reviewer
    -0.61
     Polo
    -0.59
     livest
    -0.59
    vals
    -0.59
    POSITIVE LOGITS
    ful
    1.83
    fully
    1.68
    uously
    1.25
    uous
    1.21
    fulness
    1.18
    bringer
    1.04
    iful
    1.04
    urous
    1.00
    ories
    0.98
    some
    0.97
    Activations Density 0.086%

    No Known Activations