© 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. 10-RES-JB
    11. 10243
    Prev
    Next
    INDEX
    Explanations

    phrases related to values and beliefs, particularly focusing on alignment with personal or organizational values

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or collective values

    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
    owl
    -0.72
    ilant
    -0.69
    agh
    -0.68
     Tunnel
    -0.66
    enary
    -0.65
    eor
    -0.65
    ittle
    -0.65
    dry
    -0.64
    sight
    -0.64
    availability
    -0.63
    POSITIVE LOGITS
     esp
    1.05
     tenets
    0.97
     underpin
    0.97
     beliefs
    0.96
     ideals
    0.96
     embodied
    0.95
     preached
    0.94
     clash
    0.92
     indoctr
    0.90
     guiding
    0.87
    Activations Density 0.131%

    No Known Activations