© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18137
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations, particularly ones called "avenue."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "aven" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FTA
    -0.70
     FP
    -0.66
     4096
    -0.66
     slashing
    -0.65
     tapping
    -0.64
     Frame
    -0.63
     LM
    -0.63
     leakage
    -0.62
     reversal
    -0.62
     partners
    -0.62
    POSITIVE LOGITS
    aven
    4.57
    av
    1.20
    aver
    1.17
    brew
    1.14
    avin
    1.11
    ave
    1.07
    arden
    1.05
     Aven
    1.01
    earth
    0.97
    oven
    0.96
    Activations Density 0.014%

    No Known Activations