© 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. 1-RES-JB
    6. 6396
    Prev
    Next
    INDEX
    Explanations

    terms related to digital communication tools and features

    oai_token-act-pair · gpt-3.5-turbo

    mentions of contacts or connections in a networking context

    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
    adding
    -0.77
    reci
    -0.75
    ais
    -0.71
    corn
    -0.69
    enic
    -0.67
    ft
    -0.66
    iak
    -0.65
    ffe
    -0.65
     Statue
    -0.64
    SpaceEngineers
    -0.64
    POSITIVE LOGITS
     contacts
    1.37
     contact
    0.93
     lenses
    0.93
    pring
    0.91
    hips
    0.84
    imei
    0.82
    wana
    0.81
     Contact
    0.77
     adapters
    0.74
    afety
    0.72
    Activations Density 0.006%

    No Known Activations