© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 3437
    Prev
    Next
    INDEX
    Explanations

    post numbers and related metadata in online forum posts

    oai_token-act-pair · gpt-3.5-turbo

    identifiers related to user profiles and activity metrics on social media or online platforms

    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
     staggered
    -0.66
     weap
    -0.64
     reve
    -0.62
     phys
    -0.61
     cler
    -0.61
     partners
    -0.60
     corridors
    -0.60
     paran
    -0.60
     reck
    -0.58
     brim
    -0.58
    POSITIVE LOGITS
    ################################
    1.27
    ########
    1.15
    ################
    1.05
    ###
    0.97
    bitcoin
    0.87
    region
    0.85
    define
    0.85
    MENTS
    0.83
    ³
    0.81
    !/
    0.78
    Activations Density 0.018%

    No Known Activations