© 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. 8-RES-JB
    11. 6153
    Prev
    Next
    INDEX
    Explanations

    the initials "FF" and "FM."

    oai_token-act-pair · gpt-3.5-turbo

    references to FM and FD and their associated components or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.84
     mater
    -0.74
    ask
    -0.65
     Clever
    -0.65
    lain
    -0.63
     Boone
    -0.63
    lace
    -0.62
    Els
    -0.61
    Magikarp
    -0.60
     Michaels
    -0.60
    POSITIVE LOGITS
    letcher
    1.10
    ornia
    1.08
    ruits
    0.99
    rozen
    0.94
    ruary
    0.93
    iture
    0.93
    avorable
    0.93
    ocused
    0.92
    ensibly
    0.91
    actory
    0.86
    Activations Density 0.226%

    No Known Activations