© 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. 10-RES-JB
    11. 12899
    Prev
    Next
    INDEX
    Explanations

    references to movement through a physical space

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and related phrases that indicate the presence of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upload
    -0.67
    gov
    -0.67
    NAME
    -0.66
    POSE
    -0.65
    SHARE
    -0.64
    IAN
    -0.63
    Instance
    -0.63
    CTV
    -0.63
    Lead
    -0.62
    PO
    -0.62
    POSITIVE LOGITS
     motions
    1.20
     veins
    1.14
     haze
    1.11
     gates
    1.10
     ranks
    1.10
     entirety
    1.10
     maze
    1.08
     cracks
    1.07
     hoops
    1.06
     pores
    1.02
    Activations Density 0.135%

    No Known Activations