INDEX

Explanations

terms related to declines and decreases in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

">+

-0.65

 above

-0.57

Above

-0.57

 doubled

-0.53

 Above

-0.52

Література

-0.51

бол

-0.51

emann

-0.50

makeatother

-0.50

(++

-0.50

POSITIVE LOGITS

(-)

0.83

 (−

0.80

Downs

0.78

 reductions

0.78

 onCancelled

0.76

down

0.76

]--;

0.76

 downward

0.74

 decreasing

0.74

--)

0.73

Activations Density 1.495%

terms related to declines and decreases in various contexts

No Comments

No Known Activations