© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 21841
    Prev
    Next
    INDEX
    Explanations

    phrases related to qualities or characteristics of a particular entity or subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "that," often in relation to specific qualities or characteristics of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "],
    -0.66
     Bott
    -0.64
     Explan
    -0.61
     Checking
    -0.61
     docking
    -0.59
    "],"
    -0.58
     Passive
    -0.57
     glasses
    -0.57
    .]
    -0.57
    engers
    -0.57
    POSITIVE LOGITS
     thri
    0.85
     spans
    0.82
    İĭ
    0.80
     celebrates
    0.80
     embraces
    0.79
     starved
    0.77
     lacks
    0.77
     sleeps
    0.75
    luaj
    0.75
    ĻĤ
    0.74
    Activations Density 0.185%

    No Known Activations