© 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. 2-RES-JB
    11. 4324
    Prev
    Next
    INDEX
    Explanations

    statements of feelings or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sentiment

    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
    arters
    -0.81
    ummies
    -0.71
     Eggs
    -0.68
    abb
    -0.68
     Guinness
    -0.67
    ARDS
    -0.67
    AMS
    -0.66
    ces
    -0.65
    gur
    -0.65
    ctic
    -0.65
    POSITIVE LOGITS
     sentiments
    1.15
     guiActiveUn
    1.13
     sentiment
    1.13
    ality
    0.96
    igue
    0.77
    naire
    0.74
    hovah
    0.74
    uated
    0.73
     contag
    0.72
    ilitary
    0.70
    Activations Density 0.011%

    No Known Activations