© 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. 2-RES-JB
    11. 24061
    Prev
    Next
    INDEX
    Explanations

    words related to rocks

    oai_token-act-pair · gpt-3.5-turbo

    references to "rocks" and "Zeppelins."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENTS
    -0.70
    ISC
    -0.69
    INAL
    -0.68
    EPA
    -0.68
    ========
    -0.68
    thumbnails
    -0.66
    RED
    -0.65
    CONCLUS
    -0.64
    URA
    -0.64
    EVA
    -0.63
    POSITIVE LOGITS
    cks
    1.06
    engers
    0.94
    wagon
    0.91
    kie
    0.90
    afe
    0.87
    ongs
    0.84
    mith
    0.80
    crew
    0.80
    ocks
    0.79
    ystem
    0.78
    Activations Density 0.006%

    No Known Activations