© 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. 6-RES-JB
    11. 4190
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical accounts or investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to historical analysis or discussion of overlooked figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Poké
    -0.84
     Pokemon
    -0.79
    Pokemon
    -0.76
     gym
    -0.74
     Pokémon
    -0.73
     VIP
    -0.73
    mAh
    -0.72
     respawn
    -0.71
     pit
    -0.70
     Poke
    -0.69
    POSITIVE LOGITS
     essays
    1.40
     excerpts
    1.27
     autobi
    1.13
    ibliography
    1.12
     essay
    1.11
     novelist
    1.10
     anthology
    1.08
     reprinted
    1.07
     narrator
    1.05
     Readers
    1.05
    Activations Density 0.835%

    No Known Activations