© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 9116
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital platforms and services

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "from" indicating origin or source

    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
    ratulations
    -0.80
    seek
    -0.72
    few
    -0.69
    faced
    -0.69
    lied
    -0.68
    mask
    -0.68
    aqu
    -0.68
    ascript
    -0.66
    merce
    -0.66
    quote
    -0.66
    POSITIVE LOGITS
     afar
    1.41
     whence
    1.16
     thence
    1.03
     abroad
    0.98
     scratch
    0.94
     inside
    0.86
     somewhere
    0.85
     anywhere
    0.83
     elsewhere
    0.82
     within
    0.79
    Activations Density 0.246%

    No Known Activations