© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 997
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or locations

    oai_token-act-pair · gpt-3.5-turbo

    components related to a specific cultural or artistic context

    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
     scratch
    -0.77
     mechanically
    -0.74
     crooked
    -0.70
    STD
    -0.68
    WATCH
    -0.67
     blazing
    -0.65
     fortunate
    -0.65
     weary
    -0.65
     blinding
    -0.63
     challeng
    -0.63
    POSITIVE LOGITS
    icz
    1.18
    phia
    1.15
    ai
    1.10
    alam
    1.03
    aten
    0.99
    asu
    0.98
    u
    0.98
    nir
    0.97
    ae
    0.95
    ou
    0.94
    Activations Density 0.335%

    No Known Activations