© 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. 7-RES-JB
    11. 1471
    Prev
    Next
    INDEX
    Explanations

    words related to various types of systems, tools, and management

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology, systems, and management concepts

    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
    Birth
    -0.81
    soDeliveryDate
    -0.80
    apeake
    -0.80
    Benz
    -0.79
    VOL
    -0.79
    Champ
    -0.74
    Pres
    -0.73
    Dust
    -0.73
    OFF
    -0.73
    éĹĺ
    -0.72
    POSITIVE LOGITS
     charm
    0.67
     clust
    0.65
     routines
    0.64
     brigade
    0.64
     scient
    0.63
    gered
    0.63
     cue
    0.62
    ilitating
    0.61
     supervisors
    0.61
     shenanigans
    0.60
    Activations Density 0.486%

    No Known Activations