© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7957
    Prev
    Next
    INDEX
    Explanations

    descriptions of people sitting in various locations and situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in a" followed by details of various settings or situations

    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
    Americans
    -0.78
    Effects
    -0.77
    tm
    -0.73
     Extensions
    -0.72
    omever
    -0.72
    fn
    -0.71
     beneficiaries
    -0.71
    ONEY
    -0.70
    umer
    -0.69
    stats
    -0.68
    POSITIVE LOGITS
     closet
    1.31
     darkened
    1.26
     cramped
    1.25
     cage
    1.24
     booth
    1.23
     hallway
    1.22
     coffin
    1.21
     room
    1.21
     courtyard
    1.20
     wheelchair
    1.19
    Activations Density 0.188%

    No Known Activations