INDEX

Explanations

numerical data associated with timeframes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Legg

-0.64

andExpect

-0.63

 مُعرِّف

-0.61

itinéraire

-0.60

 &___

-0.60

ので

-0.59

icated

-0.59

ResponseWriter

-0.59

Geplaatst

-0.59

thâu

-0.58

POSITIVE LOGITS

0.75

0.71

0.70

0.68

0.67

0.66

0.65

argout

0.64

️⃣

0.61

0.60

Activations Density 0.615%

numerical data associated with timeframes

No Comments

No Known Activations