© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles or reports detailing events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical data and statistics

    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
    0000000000000000
    -0.50
    iru
    -0.50
    iership
    -0.50
    ciating
    -0.49
     disadvant
    -0.47
    iverse
    -0.47
    abal
    -0.46
    azing
    -0.46
    ylum
    -0.46
    ãĤ¦ãĤ¹
    -0.46
    POSITIVE LOGITS
     meanwhile
    1.02
     however
    0.97
     also
    0.84
     therefore
    0.80
     later
    0.79
     additionally
    0.76
     subsequently
    0.75
     reportedly
    0.72
    sequently
    0.70
     moreover
    0.68
    Activations Density 1.730%

    No Known Activations