© 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. 18017
    Prev
    Next
    INDEX
    Explanations

    references to editors' notes or instructions within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "or" 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
    eas
    -0.83
    sters
    -0.72
    ITNESS
    -0.68
    lished
    -0.65
    erest
    -0.65
     daylight
    -0.61
    tp
    -0.60
    ecause
    -0.60
    lyak
    -0.60
    urned
    -0.59
    POSITIVE LOGITS
    bid
    0.88
    andom
    0.85
    ikawa
    0.81
    onto
    0.80
    SHIP
    0.80
    iasis
    0.80
    rent
    0.80
    ium
    0.80
    ially
    0.76
    izontal
    0.75
    Activations Density 0.038%

    No Known Activations