© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18095
    Prev
    Next
    INDEX
    Explanations

    mentions of outcomes and their evaluations or consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consequences or results of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     translator
    -0.77
     perfume
    -0.73
    Flag
    -0.68
    cloth
    -0.67
     blush
    -0.66
    legram
    -0.64
    Original
    -0.63
    fecture
    -0.63
    weed
    -0.63
     veil
    -0.63
    POSITIVE LOGITS
     outcomes
    3.00
     traject
    1.38
     behaviours
    1.25
     scenarios
    1.21
     behaviors
    1.20
     metrics
    1.19
     impacts
    1.17
     outputs
    1.16
     timelines
    1.15
     indicators
    1.12
    Activations Density 0.013%

    No Known Activations