© 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. 1-RES-JB
    11. 9400
    Prev
    Next
    INDEX
    Explanations

    words related to directions or positions, particularly the concept of 'side'

    oai_token-act-pair · gpt-3.5-turbo

    references to "side" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESCO
    -0.75
    ctory
    -0.75
    ancies
    -0.73
    ãģ®å®
    -0.72
    iott
    -0.70
    ctic
    -0.70
    cci
    -0.69
    ãģ®éŃĶ
    -0.68
    scl
    -0.68
    initions
    -0.68
    POSITIVE LOGITS
     side
    1.18
    side
    1.16
     Side
    1.00
    Side
    0.98
     seams
    0.83
     Za
    0.80
     undone
    0.79
     sides
    0.79
     parting
    0.76
    board
    0.74
    Activations Density 0.021%

    No Known Activations