© 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. 8-RES-JB
    6. 3970
    Prev
    Next
    INDEX
    Explanations

    adjectives describing emotions or reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional reactions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prev
    -0.67
    emer
    -0.65
    Public
    -0.59
    TI
    -0.59
    rawled
    -0.58
    ces
    -0.58
    GROUP
    -0.56
    env
    -0.56
    acist
    -0.56
    esc
    -0.56
    POSITIVE LOGITS
     myself
    1.18
     Pengu
    0.79
    poke
    0.67
     my
    0.67
     yesterday
    0.65
     seeing
    0.60
     wondering
    0.59
     parting
    0.59
     discovering
    0.58
     myster
    0.57
    Activations Density 0.388%

    No Known Activations