© 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. 11-RES-JB
    11. 15709
    Prev
    Next
    INDEX
    Explanations

    references to potential upcoming events or releases

    oai_token-act-pair · gpt-3.5-turbo

    content related to news or updates about video game releases and developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruciating
    -0.84
    ratulations
    -0.79
    ateurs
    -0.77
     appalled
    -0.75
    utterstock
    -0.73
    ¬¼
    -0.72
     constitu
    -0.70
    ickr
    -0.70
    Reviewer
    -0.69
     humiliated
    -0.67
    POSITIVE LOGITS
     rumored
    1.16
     TBA
    1.14
     upcoming
    1.11
     DLC
    1.08
     roadmap
    1.08
     forthcoming
    1.00
     NX
    1.00
     collaborations
    0.99
     TBD
    0.99
     future
    0.99
    Activations Density 0.539%

    No Known Activations