© 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. 8-RES-JB
    11. 10123
    Prev
    Next
    INDEX
    Explanations

    positive and negative aspects or consequences of situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a balance between benefits and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psc
    -0.78
    lass
    -0.78
    uca
    -0.76
    ACP
    -0.75
    ĸļ
    -0.74
     Wool
    -0.72
    ectomy
    -0.72
    ļéĨĴ
    -0.72
    apo
    -0.69
     Beet
    -0.69
    POSITIVE LOGITS
     surprises
    1.25
     flaws
    1.18
     weaknesses
    1.15
     contradictions
    1.15
     pitfalls
    1.13
     inconsistencies
    1.09
     solutions
    1.06
     twists
    1.06
     setbacks
    1.04
     timelines
    1.03
    Activations Density 0.852%

    No Known Activations