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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5403
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison, disagreement, or commentary on shared views

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reference to a group or category

    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
     disposed
    -0.65
     istg
    -0.63
    wise
    -0.63
     notwithstanding
    -0.62
     Donation
    -0.62
     Password
    -0.62
     parcel
    -0.62
     ende
    -0.61
    peed
    -0.60
     Referred
    -0.60
    POSITIVE LOGITS
    them
    0.76
    their
    0.70
    udes
    0.67
     us
    0.66
     humanity
    0.65
     those
    0.65
    those
    0.65
    arching
    0.65
    ij士
    0.64
     our
    0.64
    Activations Density 0.140%

    No Known Activations