© 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. 8117
    Prev
    Next
    INDEX
    Explanations

    references to items described as unlimited

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of unlimited quantities or capacities

    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
    RY
    -0.62
    isms
    -0.62
     Deaths
    -0.62
     Baptist
    -0.61
    pher
    -0.60
    cer
    -0.59
     Wel
    -0.58
    athing
    -0.58
    fell
    -0.57
     Mechan
    -0.57
    POSITIVE LOGITS
     unlimited
    3.82
     limitless
    2.23
     Unlimited
    1.92
     unrestricted
    1.85
     infinite
    1.82
    limited
    1.51
     endless
    1.51
     indefinite
    1.32
     unconditional
    1.27
     infinity
    1.13
    Activations Density 0.024%

    No Known Activations