© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20743
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and data processing

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to advanced technology and computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eanor
    -0.76
     Weekly
    -0.74
     Minor
    -0.73
    ername
    -0.73
    orthern
    -0.71
    auga
    -0.71
     typo
    -0.70
    ucket
    -0.69
    ename
    -0.69
    çĶ°
    -0.69
    POSITIVE LOGITS
     systems
    1.58
     machines
    1.52
     devices
    1.49
     solutions
    1.46
     technologies
    1.45
     adapters
    1.42
     architectures
    1.40
     platforms
    1.38
     interfaces
    1.37
     prototypes
    1.36
    Activations Density 0.433%

    No Known Activations