© 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 EvalsExportsinterp-engineNEWAPI 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. 11203
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations or environments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of physical locations or structures

    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
    itely
    -0.80
    forge
    -0.77
    Reloaded
    -0.73
    Reviewer
    -0.71
    oleon
    -0.68
    otropic
    -0.68
    STAR
    -0.66
    scope
    -0.66
    ForgeModLoader
    -0.66
    ulent
    -0.64
    POSITIVE LOGITS
     circa
    0.70
     littered
    0.66
     attendant
    0.65
     condol
    0.61
     clad
    0.61
     extraord
    0.60
    agall
    0.59
     alone
    0.57
     attendants
    0.57
     laced
    0.57
    Activations Density 0.467%

    No Known Activations