© 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. 0-RES-JB
    6. 586
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Amiga computer

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Amiga computer system and related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tom
    -0.67
     pat
    -0.67
     tr
    -0.64
     protector
    -0.63
     warnings
    -0.61
     Pric
    -0.60
     sprayed
    -0.60
     protected
    -0.60
     Pat
    -0.59
     trusted
    -0.59
    POSITIVE LOGITS
    iga
    4.74
    igo
    1.42
    igi
    1.37
    ig
    1.30
    ige
    1.29
    igue
    1.28
    enna
    1.17
    igan
    1.16
    uga
    1.16
    igor
    1.15
    Activations Density 0.010%

    No Known Activations