© 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. 5434
    Prev
    Next
    INDEX
    Explanations

    the word "there" used as a reference point or location indicator

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive use of the word "there" in various 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
     CJ
    -0.79
     ±
    -0.62
     Honour
    -0.61
     Braun
    -0.60
     pound
    -0.58
    ONSORED
    -0.56
     Bath
    -0.56
     Bast
    -0.55
     actionGroup
    -0.54
     cups
    -0.53
    POSITIVE LOGITS
    abouts
    1.37
    upon
    0.91
    ntil
    0.84
     fortun
    0.79
    fore
    0.76
    etheless
    0.75
    ngth
    0.75
    GoldMagikarp
    0.74
    ilst
    0.73
    olkien
    0.73
    Activations Density 0.118%

    No Known Activations