© 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. 1-RES-JB
    11. 14077
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name or mention of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    the names of characters or entities that are repeatedly mentioned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    recomm
    -0.72
    irlf
    -0.71
     personalized
    -0.66
     vested
    -0.64
     uniquely
    -0.63
     lifelong
    -0.62
     sober
    -0.62
     unrestricted
    -0.62
     weekday
    -0.62
     Home
    -0.62
    POSITIVE LOGITS
    zel
    1.21
    wald
    0.97
    baum
    0.95
    feld
    0.92
    ius
    0.90
    mann
    0.89
    bach
    0.88
    anga
    0.85
    toe
    0.84
    nuts
    0.84
    Activations Density 0.005%

    No Known Activations