© 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. 1623
    Prev
    Next
    INDEX
    Explanations

    sentences expressing efforts to address or overcome various issues or challenges

    oai_token-act-pair · gpt-3.5-turbo

    references to problems and their solutions

    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
    bos
    -0.75
    ONSORED
    -0.70
     Volunte
    -0.69
    ée
    -0.69
    apps
    -0.66
     Nanto
    -0.66
    iture
    -0.64
    opl
    -0.64
    craft
    -0.63
     Kinnikuman
    -0.62
    POSITIVE LOGITS
     problems
    1.04
     deficiencies
    1.01
     deficiency
    0.96
     grievances
    0.95
     problem
    0.93
    problem
    0.93
     woes
    0.93
     shortfall
    0.91
     dilemma
    0.90
     concerns
    0.88
    Activations Density 0.307%

    No Known Activations