© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 2880
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology, software, and internet security

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wrappers and containers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oric
    -0.80
    Beat
    -0.80
    iod
    -0.79
    enta
    -0.77
    brate
    -0.77
    alog
    -0.76
    chem
    -0.75
    romy
    -0.73
    chemical
    -0.72
    mel
    -0.72
    POSITIVE LOGITS
     wrapper
    1.06
     wra
    0.86
     Toro
    0.85
     Urug
    0.72
     Papua
    0.72
     Extras
    0.71
     Tarant
    0.70
     Trinidad
    0.70
     popcorn
    0.70
    ño
    0.69
    Activations Density 0.012%

    No Known Activations