© 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. 16766
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "acy" or phrases related to a pharmacy or medication context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fallacies and biases

    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
     superhuman
    -0.69
    Ń·
    -0.65
    LEASE
    -0.65
     rgb
    -0.65
     compassionate
    -0.60
     molded
    -0.60
    cedented
    -0.60
     sequest
    -0.60
    ACTED
    -0.59
     evenly
    -0.59
    POSITIVE LOGITS
    acy
    1.35
    ility
    0.89
    acies
    0.84
    acia
    0.81
    edia
    0.81
    rics
    0.79
    uous
    0.78
    utic
    0.77
    oux
    0.76
    ibility
    0.75
    Activations Density 0.012%

    No Known Activations