© 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. 2-RES-JB
    11. 14051
    Prev
    Next
    INDEX
    Explanations

    phrases related to "av" or words with "av" as a prefix

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "av" in different contexts

    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
    LOAD
    -0.73
    FORMATION
    -0.66
    FORE
    -0.65
     towels
    -0.65
     fracturing
    -0.65
    Else
    -0.64
     Barnett
    -0.64
     Prin
    -0.62
    FINE
    -0.62
    hyde
    -0.62
    POSITIVE LOGITS
    atars
    1.18
    iew
    1.07
    ionics
    1.05
    iste
    1.03
    ille
    1.03
    ial
    0.93
    igr
    0.92
    ascular
    0.92
    aro
    0.92
    anas
    0.92
    Activations Density 0.006%

    No Known Activations