© 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. 7-RES-JB
    11. 21282
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or actions happening

    oai_token-act-pair · gpt-3.5-turbo

    topics related to healthcare and policy changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -)
    -0.84
    Reviewer
    -0.68
    vation
    -0.62
    #$
    -0.60
     gospel
    -0.59
     VIDEOS
    -0.58
    !)
    -0.57
    )</
    -0.56
    CONCLUS
    -0.55
    !).
    -0.53
    POSITIVE LOGITS
     2020
    0.75
     2021
    0.74
     escalating
    0.70
     2022
    0.70
     2024
    0.68
     2019
    0.66
     Nato
    0.65
     amid
    0.64
     citing
    0.62
     overseas
    0.61
    Activations Density 0.782%

    No Known Activations