© 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. 3-RES-JB
    6. 8767
    Prev
    Next
    INDEX
    Explanations

    words related to reality and perception

    oai_token-act-pair · gpt-3.5-turbo

    abstract nouns related to concepts and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neut
    -0.69
     underwater
    -0.65
     whisk
    -0.62
    UCT
    -0.61
    blogspot
    -0.60
     conv
    -0.60
     behold
    -0.60
     nostalgic
    -0.59
     cum
    -0.59
    paces
    -0.59
    POSITIVE LOGITS
     Advice
    0.94
     Advisory
    0.91
     Assistance
    0.86
     Analysis
    0.86
     Response
    0.79
    anyahu
    0.78
     Explan
    0.78
     Tactics
    0.78
     Oversight
    0.78
     Authority
    0.78
    Activations Density 0.130%

    No Known Activations