© 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. 7-RES-JB
    6. 229
    Prev
    Next
    INDEX
    Explanations

    instances of a specific location mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "there"

    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
    eer
    -0.61
    usterity
    -0.56
     Bundy
    -0.54
     cups
    -0.53
     +/-
    -0.53
     buff
    -0.52
     psy
    -0.51
     whiff
    -0.51
     tonnes
    -0.51
    VALUE
    -0.51
    POSITIVE LOGITS
    abouts
    1.94
    upon
    1.21
    tics
    0.88
    with
    0.81
    fore
    0.80
     illegally
    0.79
    after
    0.78
    from
    0.77
    for
    0.77
     guiActiveUn
    0.77
    Activations Density 0.071%

    No Known Activations