© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 5563
    Prev
    Next
    INDEX
    Explanations

    phrases related to selecting or choosing between different options

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or movements associated with 'kick' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONT
    -0.66
    ç¥ŀ
    -0.62
     lobe
    -0.62
     Schne
    -0.61
    ational
    -0.59
     Corvette
    -0.56
     Superior
    -0.56
     warr
    -0.56
     unfocusedRange
    -0.56
     glac
    -0.55
    POSITIVE LOGITS
    icking
    1.04
    icked
    1.00
    icks
    0.86
    ivated
    0.83
    culosis
    0.78
    ilver
    0.77
    elist
    0.76
    ety
    0.75
    otine
    0.74
    urated
    0.74
    Activations Density 0.007%

    No Known Activations