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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 7015
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, titles, and positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to corporate and media entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shannon
    -0.89
     Playstation
    -0.86
     Snapchat
    -0.84
     psi
    -0.83
     PlayStation
    -0.80
     Pokemon
    -0.78
     Chapel
    -0.77
     Chev
    -0.77
    shit
    -0.76
     chi
    -0.75
    POSITIVE LOGITS
     Ed
    1.19
     Edwards
    1.18
     ED
    1.17
    Ed
    1.15
    uld
    1.06
    idd
    1.06
    ID
    1.05
    alde
    1.04
    aid
    1.03
    id
    1.02
    Activations Density 0.384%

    No Known Activations