© 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. 4-RES-JB
    11. 7494
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings of sadness or disappointment

    oai_token-act-pair · gpt-3.5-turbo

    words related to aircraft or aviation themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 4 - sadness

    No Comments

    Negative Logits
     Macy
    -0.65
     characteristic
    -0.64
     adv
    -0.63
     manner
    -0.63
     Dept
    -0.62
     Clo
    -0.62
     haste
    -0.61
     requisite
    -0.60
     Spiel
    -0.60
     backdoor
    -0.59
    POSITIVE LOGITS
    ombat
    0.89
    owship
    0.84
    eps
    0.83
    cheon
    0.81
    parts
    0.76
    FACE
    0.74
    pload
    0.73
    roid
    0.72
    anon
    0.71
    puff
    0.71
    Activations Density 0.062%

    No Known Activations