© 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. 18811
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of physical objects

    oai_token-act-pair · gpt-3.5-turbo

    specific devices and their positive attributes

    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
    alties
    -0.92
    blogs
    -0.90
    Jews
    -0.90
    Muslims
    -0.85
    Population
    -0.84
    Dialogue
    -0.83
    idelines
    -0.83
     Cosponsors
    -0.82
    aucuses
    -0.82
    aneers
    -0.80
    POSITIVE LOGITS
     device
    1.51
     product
    1.47
     beast
    1.33
     machine
    1.32
     gadget
    1.26
     item
    1.25
     unit
    1.24
     model
    1.23
     thing
    1.20
     chassis
    1.19
    Activations Density 0.294%

    No Known Activations