© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17770
    Prev
    Next
    INDEX
    Explanations

    mentions of the drug "Amphetamine" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Amiga."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corners
    -0.79
     Crus
    -0.79
    ãģį
    -0.75
     Subtle
    -0.71
     tobacco
    -0.69
     mushrooms
    -0.69
     Titanic
    -0.68
     behav
    -0.67
    vous
    -0.65
     Wick
    -0.65
    POSITIVE LOGITS
    sterdam
    1.31
    endment
    1.26
    nesty
    1.23
    ateur
    1.18
    ethyst
    1.12
    elia
    1.05
    assador
    1.00
    borgh
    1.00
    essage
    0.98
    urai
    0.96
    Activations Density 0.007%

    No Known Activations