© 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. 7-RES-JB
    11. 12564
    Prev
    Next
    INDEX
    Explanations

    keywords related to projects, initiatives, and plans

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to contentious projects and proposals

    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
    gment
    -0.76
    gments
    -0.73
    gements
    -0.70
    ception
    -0.69
    anuts
    -0.68
    notations
    -0.67
    estine
    -0.65
    utation
    -0.65
    ahime
    -0.64
    pointer
    -0.64
    POSITIVE LOGITS
     POLITICO
    0.80
     NCT
    0.69
     insiders
    0.67
     Deadline
    0.66
     Politico
    0.66
     feds
    0.66
     unveiling
    0.62
     lobbyists
    0.62
     activists
    0.62
     hints
    0.61
    Activations Density 1.084%

    No Known Activations