INDEX

Explanations

scientific terminology and concepts related to health or medical conditions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 насељу

-0.64

AddHtmlAttribute

-0.61

ⓧ

-0.61

+#+#

-0.58

ضاف

-0.49

hot

-0.48

aarrggbb

-0.47

NameInMap

-0.47

AddField

-0.46

POSITIVE LOGITS

CodeAttribute

0.97

 purpoſe

0.89

 itſelf

0.86

 pleaſure

0.81

 ſta

0.79

 becauſe

0.77

 himſelf

0.76

 Reſ

0.75

 greateſt

0.74

 Chriftian

0.74

Activations Density 0.021%

scientific terminology and concepts related to health or medical conditions

No Comments

No Known Activations