© 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. 8-RES-JB
    11. 8574
    Prev
    Next
    INDEX
    Explanations

    phrases related to dates and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating prerequisites or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.79
    uminati
    -0.68
     Subtle
    -0.67
    microsoft
    -0.61
    enary
    -0.60
    chant
    -0.60
    ':
    -0.60
    =-=-=-=-
    -0.58
    âĹ¼
    -0.58
    bleacher
    -0.57
    POSITIVE LOGITS
    sequently
    1.05
    sequent
    0.91
     ensuing
    0.80
    quartered
    0.78
    cknowled
    0.73
     thereafter
    0.72
     however
    0.72
     latter
    0.71
    Additionally
    0.69
     therefore
    0.68
    Activations Density 0.457%

    No Known Activations