© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 17
    Prev
    Next
    INDEX
    Explanations

    references to streaming services or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of streaming activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     misunderstanding
    -0.81
     reluct
    -0.74
    nces
    -0.68
     misunder
    -0.68
    ailability
    -0.68
     relativity
    -0.63
    DonaldTrump
    -0.61
    akespe
    -0.61
    chy
    -0.60
     lockdown
    -0.60
    POSITIVE LOGITS
    lining
    1.25
    stream
    1.00
    lined
    0.97
     Stream
    0.96
    line
    0.90
    liner
    0.89
    lines
    0.88
    ãĤ§
    0.84
    embed
    0.83
    )=(
    0.81
    Activations Density 0.010%

    No Known Activations