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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 4-RES-JB
    6. 17997
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to journals or publications

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Journal" or its variations, indicating references to journals or publications

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

    No Comments

    Negative Logits
    holders
    -0.69
     ours
    -0.67
     theirs
    -0.63
    ayers
    -0.61
    cream
    -0.61
    creen
    -0.60
     regress
    -0.59
    dh
    -0.59
     Michele
    -0.59
     continents
    -0.58
    POSITIVE LOGITS
     Sentinel
    0.96
    ournals
    0.92
    istic
    0.90
     Editors
    0.84
     Journal
    0.84
    istically
    0.82
    ism
    0.81
    Journal
    0.81
    Paper
    0.81
    etta
    0.79
    Activations Density 0.011%

    No Known Activations