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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15074
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software compatibility and support

    oai_token-act-pair · gpt-3.5-turbo

    references to software compatibility and support features

    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
    escription
    -0.92
    ÄŁ
    -0.80
    INESS
    -0.80
    incerity
    -0.80
    lah
    -0.79
    conserv
    -0.79
    earchers
    -0.78
    ossession
    -0.78
    chel
    -0.76
    ihu
    -0.76
    POSITIVE LOGITS
     hardware
    1.20
     Windows
    1.18
     NVIDIA
    1.14
     Linux
    1.12
     firmware
    1.10
     CPUs
    1.09
     Nvidia
    1.08
     DirectX
    1.06
     Android
    1.06
     GPUs
    1.05
    Activations Density 0.395%

    No Known Activations