© 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. 2701
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to specific locations or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "the scene" and related contexts

    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
    naire
    -0.69
    izoph
    -0.68
    ratulations
    -0.67
    Measure
    -0.66
    arius
    -0.65
    å¹
    -0.64
    sylv
    -0.62
    ata
    -0.62
    [_
    -0.61
    lance
    -0.61
    POSITIVE LOGITS
     scene
    1.27
     behest
    1.18
     site
    1.15
     outset
    1.13
     intersection
    1.07
     helm
    1.05
     entrance
    1.04
     forefront
    1.03
     entrances
    1.02
     facility
    0.99
    Activations Density 0.130%

    No Known Activations