Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22733
    Prev
    Next
    INDEX
    Explanations

    references to the programming language and database management system "MongoDB"

    oai_token-act-pair · gpt-3.5-turbo

    references to the MongoDB database and associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -1.03
    y
    -0.96
    ea
    -0.83
    edly
    -0.75
    ded
    -0.71
    dit
    -0.70
    mble
    -0.70
    d
    -0.69
    ed
    -0.69
    xual
    -0.69
    POSITIVE LOGITS
    istic
    1.07
    istics
    1.01
    omach
    1.01
    osaurs
    0.99
    aries
    0.96
    istically
    0.94
    ograms
    0.93
    osa
    0.89
    ocy
    0.88
    oco
    0.88
    Activations Density 0.245%

    No Known Activations