© 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. 9-RES-JB
    11. 7491
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities of entities such as employees, followers, and members

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to the size and scale of organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shocks
    -0.71
    fter
    -0.68
    Ĥİ
    -0.67
    ãĤ¹ãĥĪ
    -0.66
     compromises
    -0.64
     adversity
    -0.61
     liberties
    -0.60
    rams
    -0.58
     screams
    -0.58
    later
    -0.58
    POSITIVE LOGITS
    quartered
    0.94
     holdings
    0.87
     stationed
    0.87
     active
    0.78
    DAQ
    0.78
     registered
    0.77
    ournals
    0.76
     devoted
    0.76
     dedicated
    0.75
     headquartered
    0.73
    Activations Density 0.551%

    No Known Activations