INDEX

Explanations

references to medical conditions and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

脚注の使い方

-0.73

ItemBackground

-0.69

 OFDb

-0.63

AddTagHelper

-0.63

 Hiram

-0.60

 purpoſe

-0.59

 pleaſure

-0.59

Hochspringen

-0.59

 Shakspeare

-0.58

 Cister

-0.57

POSITIVE LOGITS

 including

0.84

 such

0.84

 namely

0.69

eg

0.68

such

0.67

 like

0.64

 include

0.63

 pinulongan

0.61

—

0.60

Activations Density 0.743%

references to medical conditions and their implications

No Comments

No Known Activations