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

    Neuronpedia

    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. 1-RES-JB
    11. 21047
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "rocks" or "rocking"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to blocks or chunks of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENTS
    -0.77
    EVA
    -0.76
    URA
    -0.70
    INAL
    -0.69
    ENT
    -0.64
    ROR
    -0.64
    äº
    -0.64
    ISC
    -0.63
    ACTED
    -0.63
    EMBER
    -0.63
    POSITIVE LOGITS
    cks
    1.36
    kie
    0.96
    engers
    0.91
    wagon
    0.91
    kies
    0.90
    steen
    0.89
    sburgh
    0.87
    mith
    0.82
    utsche
    0.78
    ansas
    0.78
    Activations Density 0.005%

    No Known Activations