© 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. 9-RES-JB
    11. 3314
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations or settings, particularly those with visual descriptions

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases related to locations and environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.94
    cia
    -0.74
    phrine
    -0.73
    otonin
    -0.70
    anol
    -0.70
    assad
    -0.70
    obook
    -0.69
    utonium
    -0.68
    ipolar
    -0.67
    anguage
    -0.63
    POSITIVE LOGITS
     vicinity
    1.22
     streets
    1.22
     rooft
    1.21
     sidewalks
    1.21
     horizon
    1.19
     corners
    1.17
     entrances
    1.15
     passers
    1.14
     hills
    1.10
     balcon
    1.09
    Activations Density 0.409%

    No Known Activations