© 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. 0-RES-JB
    11. 6812
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities that hold a specific position or ownership

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate possession or control

    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
    ocom
    -0.73
    icken
    -0.73
    coded
    -0.64
    pport
    -0.62
    enza
    -0.61
    obin
    -0.59
    emphasis
    -0.58
    ourced
    -0.57
    UX
    -0.55
    night
    -0.54
    POSITIVE LOGITS
     holds
    3.37
     hold
    2.05
     held
    1.66
     Hold
    1.63
    hold
    1.53
     holding
    1.47
     maintains
    1.40
     retains
    1.37
    Hold
    1.37
     sits
    1.36
    Activations Density 0.016%

    No Known Activations