© 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. 6212
    Prev
    Next
    INDEX
    Explanations

    words or acronyms containing 'af'

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of 'af' or 'af' as a prefix

    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
     Dru
    -0.68
     Patriarch
    -0.68
     Morg
    -0.62
     Hulk
    -0.62
     fixation
    -0.61
     Olymp
    -0.59
     Fargo
    -0.59
     Breaker
    -0.58
     MLG
    -0.58
     Divinity
    -0.58
    POSITIVE LOGITS
    rican
    1.39
    rica
    1.23
    ayette
    1.19
    riend
    1.16
    amily
    1.14
    rost
    1.14
    eatures
    1.13
    ornia
    1.12
    avorite
    1.12
    eteria
    1.06
    Activations Density 0.022%

    No Known Activations