© 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. 7-RES-JB
    11. 12421
    Prev
    Next
    INDEX
    Explanations

    terms related to specific locations, particularly ones with the word "Park" in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Park" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dilig
    -0.87
    Downloadha
    -0.83
    nces
    -0.82
    apter
    -0.74
     pneum
    -0.74
    acist
    -0.72
    interstitial
    -0.71
    nant
    -0.67
    icter
    -0.64
    adeon
    -0.63
    POSITIVE LOGITS
    hurst
    0.97
     Zoo
    0.91
    walking
    0.89
    park
    0.86
    walk
    0.84
     Rangers
    0.83
    itect
    0.78
    walker
    0.77
    our
    0.77
    lease
    0.75
    Activations Density 0.021%

    No Known Activations