© 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 EvalsExportsAPI 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. 4909
    Prev
    Next
    INDEX
    Explanations

    phrases related to holding or grasping tightly

    oai_token-act-pair · gpt-3.5-turbo

    words related to clutches and gorillas, indicating a focus on themes of grasping or holding and their connection to gorilla references

    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
    earch
    -0.85
    esian
    -0.84
    oples
    -0.81
    Rad
    -0.74
    arbon
    -0.74
     Outs
    -0.72
    es
    -0.72
    manship
    -0.71
    hire
    -0.70
    eker
    -0.70
    POSITIVE LOGITS
    iously
    0.80
    tered
    0.76
    tle
    0.75
    isle
    0.72
    ulously
    0.72
    ifully
    0.71
    ches
    0.71
    oxin
    0.71
     purse
    0.70
     Kut
    0.69
    Activations Density 0.032%

    No Known Activations