© 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. 7-RES-JB
    11. 13072
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology interfaces and connectors

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications related to USB and SD card connectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    áµ
    -0.77
     Fallen
    -0.73
    zanne
    -0.73
    EY
    -0.70
     judgments
    -0.70
    eworld
    -0.67
    sted
    -0.67
     Judgment
    -0.67
    atural
    -0.67
    rikes
    -0.67
    POSITIVE LOGITS
     adapter
    1.26
     connector
    1.17
     adapters
    1.13
    USB
    1.12
     Adapter
    1.08
    Accessory
    1.08
     connectors
    1.07
     USB
    1.06
     charger
    1.06
     cable
    1.06
    Activations Density 0.185%

    No Known Activations