© 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. 2-RES-JB
    6. 8435
    Prev
    Next
    INDEX
    Explanations

    words related to physical locations, specifically ports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avid
    -0.69
    APH
    -0.64
    pta
    -0.64
    ById
    -0.64
     Bears
    -0.61
     Void
    -0.61
    awks
    -0.61
    andel
    -0.60
    qqa
    -0.59
    reditary
    -0.58
    POSITIVE LOGITS
    ugal
    1.20
    folios
    1.10
    folio
    1.01
    rait
    0.97
    raits
    0.87
    ilage
    0.77
     port
    0.75
    onet
    0.73
     ported
    0.73
    itional
    0.72
    Activations Density 0.010%

    No Known Activations