© 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. 4-RES-JB
    6. 13277
    Prev
    Next
    INDEX
    Explanations

    phrases indicating satisfaction or approval

    oai_token-act-pair · gpt-3.5-turbo

    expressions of satisfaction or approval

    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
    Not in Any Lists

    No Comments

    Negative Logits
    opic
    -0.90
    plane
    -0.74
    ngth
    -0.72
    hang
    -0.70
     hijacked
    -0.66
    sites
    -0.66
     mater
    -0.65
    opers
    -0.65
    facts
    -0.65
    çīĪ
    -0.64
    POSITIVE LOGITS
    joy
    0.74
     onlook
    0.72
    NESS
    0.71
     birthday
    0.70
    vale
    0.70
     Parish
    0.69
    urous
    0.68
     pleased
    0.67
    iated
    0.67
     delighted
    0.66
    Activations Density 0.023%

    No Known Activations