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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 17046
    Prev
    Next
    INDEX
    Explanations

    specific areas or locations mentioned within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or positions within a layout

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.81
    abl
    -0.73
    rig
    -0.69
    aughs
    -0.68
    Class
    -0.65
    thood
    -0.65
    fest
    -0.65
    bags
    -0.63
    lig
    -0.62
    RANT
    -0.61
    POSITIVE LOGITS
     underside
    1.38
     verge
    1.18
     outskirts
    1.10
     opposite
    1.08
     horizon
    1.07
     sides
    1.07
     periphery
    1.06
     left
    1.05
     bottom
    1.02
     brink
    1.01
    Activations Density 0.111%

    No Known Activations