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. 9-RES-JB
    6. 20502
    Prev
    Next
    INDEX
    Explanations

    verbs related to investigations or reviews

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to carrying out formal actions or investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.68
     rappers
    -0.67
     mates
    -0.65
     prizes
    -0.63
    being
    -0.62
    lords
    -0.62
     attendees
    -0.62
     dudes
    -0.62
    coins
    -0.61
     adherents
    -0.61
    POSITIVE LOGITS
     consultation
    1.12
     investigation
    1.04
     feasibility
    1.02
     survey
    1.01
     preliminary
    0.99
     reconnaissance
    0.98
     retrospective
    0.97
     inquiry
    0.95
     exhaustive
    0.94
     consultations
    0.94
    Activations Density 0.347%

    No Known Activations