© 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. 10-RES-JB
    6. 2961
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing strong opinions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives indicating positive or negative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    steps
    -0.84
    Americans
    -0.79
    Os
    -0.79
    ipples
    -0.78
    events
    -0.75
    ques
    -0.75
     Machines
    -0.74
    attacks
    -0.73
    objects
    -0.73
    Nazis
    -0.73
    POSITIVE LOGITS
     reputation
    1.42
     knack
    1.41
     tendency
    1.30
     penchant
    1.29
     grasp
    1.24
     arsenal
    1.16
     repertoire
    1.14
     relationship
    1.12
     propensity
    1.12
     habit
    1.11
    Activations Density 0.163%

    No Known Activations