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. 6178
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events involving movement or transition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transition or movement into new states or places

    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
     occasions
    -0.69
    iam
    -0.68
    mates
    -0.68
    ingly
    -0.67
    eers
    -0.64
    utm
    -0.63
    oji
    -0.63
    FactoryReloaded
    -0.62
    wcsstore
    -0.62
    anz
    -0.60
    POSITIVE LOGITS
     fray
    1.49
     bloodstream
    1.13
     abyss
    1.11
     midst
    1.08
     realm
    1.04
     vortex
    1.00
     groove
    0.98
     weeds
    0.93
     trap
    0.93
     strat
    0.92
    Activations Density 0.244%

    No Known Activations