© 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. 22407
    Prev
    Next
    INDEX
    Explanations

    phrases related to check-in procedures and related systems

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and directional phrases associated with movement

    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
    APH
    -0.78
    ANY
    -0.77
    wordpress
    -0.72
    aido
    -0.72
    cod
    -0.72
    illac
    -0.71
    bard
    -0.71
    ulet
    -0.71
    ighth
    -0.70
    grave
    -0.69
    POSITIVE LOGITS
     mechanism
    0.88
     mentality
    0.86
     scenario
    0.83
     attitude
    0.82
     arrangement
    0.75
     effect
    0.75
     syndrome
    0.75
    cation
    0.74
     affair
    0.73
     extraord
    0.72
    Activations Density 0.144%

    No Known Activations