INDEX

Explanations

elements and methods related to message handling and object manipulation in programming contexts

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

Clearing optional data/messages

np_acts-logits-general · gemini-2.0-flash

clearing or resetting values

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

__(/*!

-0.74

 autorytatywna

-0.72

 للاسماء

-0.66

rungsseite

-0.65

üyada

-0.64

++;

-0.63

 ExecuteAsync

-0.63

]+=

-0.62

++){

-0.61

POSITIVE LOGITS

 reset

0.97

reset

0.84

Reset

0.81

 Reset

0.81

 resets

0.75

 disappear

0.71

 resetting

0.71

 disappeared

0.69

 RESET

0.68

 emptied

0.68

Activations Density 0.066%

elements and methods related to message handling and object manipulation in programming contexts

Clearing optional data/messages

clearing or resetting values

No Comments

No Known Activations