© 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. 7100
    Prev
    Next
    INDEX
    Explanations

    phrases related to software or technology and their ease of use

    oai_token-act-pair · gpt-3.5-turbo
    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
     Rasmussen
    -0.66
     Brach
    -0.64
     Bundy
    -0.63
     hur
    -0.62
    ļéĨĴ
    -0.62
    dogs
    -0.61
    nesty
    -0.60
     Sheep
    -0.60
     Relief
    -0.59
    LEY
    -0.59
    POSITIVE LOGITS
     navigate
    1.17
     grasp
    1.10
     understand
    1.09
     customize
    1.09
     learn
    1.05
     configure
    1.03
     administer
    1.03
    use
    1.03
     digest
    1.02
     comprehend
    1.00
    Activations Density 0.066%

    No Known Activations