© 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. 4-RES-JB
    11. 10254
    Prev
    Next
    INDEX
    Explanations

    phrases related to the medication 'escitalopram', such as its uses, effects, and experiences

    oai_token-act-pair · gpt-3.5-turbo

    variations of the term "escape."

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

    No Comments

    Negative Logits
     Monthly
    -0.67
    Downloadha
    -0.65
    ãĥĦ
    -0.65
    winner
    -0.64
    gran
    -0.63
    boys
    -0.63
    ĪĴ
    -0.63
    è¦ļéĨĴ
    -0.62
    beard
    -0.62
    è£ħ
    -0.62
    POSITIVE LOGITS
    aped
    1.28
    ribed
    1.25
    apes
    1.15
    ript
    1.10
    ence
    1.09
    enced
    1.03
    apers
    1.01
    utions
    0.99
    opes
    0.99
    orts
    0.97
    Activations Density 0.006%

    No Known Activations