© 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
    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. 12582
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing joy, support, or approval through enthusiastic vocalization

    oai_token-act-pair · gpt-3.5-turbo

    references to expressions of support or encouragement

    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
    ngth
    -0.70
     acquaintance
    -0.65
    course
    -0.64
     fung
    -0.64
    ahime
    -0.63
    interstitial
    -0.61
    amation
    -0.60
    uture
    -0.60
    copy
    -0.60
    orgetown
    -0.59
    POSITIVE LOGITS
    leaders
    1.43
    leader
    1.36
    leading
    1.32
    lead
    1.20
    fulness
    1.04
     cheer
    1.04
     cheering
    0.94
    fully
    0.92
    hovah
    0.91
    rous
    0.87
    Activations Density 0.030%

    No Known Activations