© 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. 11-RES-JB
    11. 24172
    Prev
    Next
    INDEX
    Explanations

    words related to skills and attributes like spotting talent and being overlooked

    oai_token-act-pair · gpt-3.5-turbo

    verb forms indicating states of being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctors
    -0.76
     TABLE
    -0.68
     CPC
    -0.67
     Topic
    -0.66
     Discussion
    -0.65
     conspiracy
    -0.65
     Situation
    -0.64
    former
    -0.64
    naire
    -0.64
     fiasco
    -0.63
    POSITIVE LOGITS
     rewarded
    1.24
     contagious
    1.20
     evident
    1.19
     outwe
    1.17
     undeniable
    1.17
     appreciated
    1.15
     unmatched
    1.10
     palpable
    1.08
     achieved
    1.07
     apparent
    1.07
    Activations Density 0.258%

    No Known Activations