Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 24264
    Prev
    Next
    INDEX
    Explanations

    positive and negative emotional expressions related to actions taken by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    emotional responses and varying intensities of feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Avenger
    -0.69
    ode
    -0.67
    itta
    -0.63
     Sleeping
    -0.62
     Valkyrie
    -0.60
     SG
    -0.60
     Investigations
    -0.59
     FS
    -0.59
     SI
    -0.59
     NR
    -0.58
    POSITIVE LOGITS
     strokes
    0.82
     abandon
    0.76
    fare
    0.75
    itud
    0.74
    idious
    0.74
     srfAttach
    0.74
     flourish
    0.74
     stroke
    0.73
     whim
    0.72
    locks
    0.70
    Activations Density 0.331%

    No Known Activations