© 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. 0-RES-JB
    6. 19952
    Prev
    Next
    INDEX
    Explanations

    references to anniversary dates or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anniversaries and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beg
    -0.69
     scrim
    -0.65
     Videos
    -0.64
    ulent
    -0.61
    iants
    -0.61
     vectors
    -0.61
     gull
    -0.60
    idth
    -0.60
     quotas
    -0.59
    Je
    -0.59
    POSITIVE LOGITS
     Anniversary
    2.92
    canon
    2.37
    nex
    1.62
    teness
    1.15
     Funk
    1.10
    birth
    1.07
    iversary
    1.07
     Omega
    0.96
    roma
    0.87
     Myster
    0.85
    Activations Density 0.040%

    No Known Activations