© 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. 9-RES-JB
    11. 16364
    Prev
    Next
    INDEX
    Explanations

    terms related to formal information exchange or communication

    oai_token-act-pair · gpt-3.5-turbo

    references to briefings or official meetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abram
    -0.67
     mating
    -0.65
    relative
    -0.64
    adia
    -0.63
    alde
    -0.63
    adic
    -0.62
     adultery
    -0.62
    acea
    -0.62
    anto
    -0.61
    oping
    -0.60
    POSITIVE LOGITS
     briefings
    1.13
     briefing
    0.95
     sessions
    0.88
     Papers
    0.84
     session
    0.76
    cation
    0.75
    heit
    0.74
     convened
    0.74
     slides
    0.73
     room
    0.73
    Activations Density 0.056%

    No Known Activations