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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 2242
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and international affairs

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidx
    -0.62
    linger
    -0.60
     sqor
    -0.60
    cffffcc
    -0.58
    oother
    -0.57
     Originally
    -0.54
    surprisingly
    -0.54
     Cosponsors
    -0.53
    ickr
    -0.53
    olog
    -0.52
    POSITIVE LOGITS
     humankind
    0.67
     mankind
    0.65
     humanity
    0.61
     civilisation
    0.57
     Buddhism
    0.56
     outcome
    0.55
     conformity
    0.55
     sorts
    0.53
     Christianity
    0.53
     our
    0.52
    Activations Density 0.949%

    No Known Activations