INDEX

Explanations

words related to stopping or halting actions, particularly in the context of traffic signs or commands

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

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

 EconPapers

-0.83

ItemBackground

-0.80

:✨

-0.79

 HasFactory

-0.76

plier

-0.75

 الحره

-0.72

DockStyle

-0.71

 linkovi

-0.70

]))

-0.69

 שוליים

-0.69

POSITIVE LOGITS

 Stops

0.96

 STOP

0.94

 stops

0.93

 Stop

0.88

STOP

0.88

 stop

0.85

stops

0.85

Stop

0.83

stop

0.80

Stops

0.79

Activations Density 0.074%

words related to stopping or halting actions, particularly in the context of traffic signs or commands

No Comments

No Known Activations