© 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. 9-RES-JB
    11. 18415
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe a person, such as "believable" or "spectacular."

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to notable characteristics and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cascade
    -0.59
    ©¶æ
    -0.59
     Pledge
    -0.58
    insula
    -0.57
    ARB
    -0.57
     revolving
    -0.55
     frenzy
    -0.55
     deposition
    -0.53
    ourt
    -0.53
    ocations
    -0.53
    POSITIVE LOGITS
     enough
    1.13
    enough
    1.02
     incarn
    0.95
    ulously
    0.85
    aneously
    0.84
     Enough
    0.78
    enged
    0.78
    ishly
    0.78
     insofar
    0.76
    ãĤ´
    0.75
    Activations Density 0.342%

    No Known Activations