© 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. 22716
    Prev
    Next
    INDEX
    Explanations

    the phrase "come back"

    oai_token-act-pair · gpt-3.5-turbo

    the word "back" 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
     Conrad
    -0.66
     Crowd
    -0.66
     delegation
    -0.64
    "]=>
    -0.64
     prerequisite
    -0.64
     rollout
    -0.63
     understatement
    -0.62
     Hacker
    -0.62
     Bunker
    -0.61
    ahime
    -0.60
    POSITIVE LOGITS
    doors
    0.88
    packs
    0.86
     alive
    0.84
    door
    0.84
    home
    0.81
    tracking
    0.81
    stab
    0.77
    seat
    0.75
    nir
    0.74
    rub
    0.74
    Activations Density 0.028%

    No Known Activations