© 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. 4-RES-JB
    11. 12536
    Prev
    Next
    INDEX
    Explanations

    words related to spatial and temporal information or dimensions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spatial and temporal concepts

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

    No Comments

    Negative Logits
    ortium
    -0.84
    doms
    -0.77
    jri
    -0.76
    mber
    -0.76
    regon
    -0.75
    rug
    -0.74
    inion
    -0.74
    EGA
    -0.74
    vous
    -0.72
    rology
    -0.70
    POSITIVE LOGITS
    ities
    1.06
     spatial
    1.03
     dimensions
    0.86
     distortions
    0.85
     lobe
    0.82
    atial
    0.82
     cues
    0.81
     aber
    0.81
     landmarks
    0.81
     proximity
    0.79
    Activations Density 0.013%

    No Known Activations