© 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. 11305
    Prev
    Next
    INDEX
    Explanations

    mentions of the location where someone is currently residing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the preposition "in."

    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
    ional
    -0.83
    tons
    -0.69
    soever
    -0.68
     importantly
    -0.66
     incumb
    -0.65
     surpr
    -0.65
     therein
    -0.63
    /(
    -0.63
     endors
    -0.63
    llor
    -0.63
    POSITIVE LOGITS
     lieu
    1.22
    patient
    1.18
     vitro
    1.03
     accordance
    1.00
    activity
    0.95
     spite
    0.94
     situ
    0.92
     vain
    0.91
    animate
    0.89
     order
    0.88
    Activations Density 0.352%

    No Known Activations