© 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. 3209
    Prev
    Next
    INDEX
    Explanations

    phrases related to official documents like transcripts and regulations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transcripts and selection processes

    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
     visitation
    -0.66
     Angels
    -0.64
    UNCH
    -0.62
     Tomas
    -0.61
    VERSION
    -0.59
     exception
    -0.58
     Braun
    -0.58
    DERR
    -0.57
     LIFE
    -0.57
     BIT
    -0.57
    POSITIVE LOGITS
    cript
    1.14
    osate
    1.03
    icter
    0.99
    ivated
    0.93
    alid
    0.92
    illian
    0.90
    naire
    0.89
    orsi
    0.89
    anooga
    0.89
    eus
    0.89
    Activations Density 0.010%

    No Known Activations