© 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. 14657
    Prev
    Next
    INDEX
    Explanations

    references to the word "ander" combined with preceding words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Chander" 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
     tremend
    -0.73
    ĪĴ
    -0.71
    ccording
    -0.71
    ded
    -0.69
    urious
    -0.68
    ured
    -0.65
    eller
    -0.65
    ruary
    -0.65
    encers
    -0.64
    ered
    -0.63
    POSITIVE LOGITS
    bilt
    1.37
    lust
    0.93
    FTWARE
    0.86
    thal
    0.82
    indal
    0.81
    xual
    0.78
    berries
    0.78
    ;;;;;;;;;;;;
    0.78
    berry
    0.74
     Spoon
    0.74
    Activations Density 0.030%

    No Known Activations