INDEX

Explanations

references to analysis and examination of data

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

足

-0.67

 thú

-0.65

 Roper

-0.63

덟

-0.63

Imm

-0.61

mort

-0.61

Ordinal

-0.60

 Entrepre

-0.60

Bur

-0.59

dde

-0.59

POSITIVE LOGITS

 analyses

1.43

 Analyses

1.42

 analys

1.34

Analyses

1.33

 analysis

1.23

ANALYSIS

1.17

 analyzes

1.15

 analyse

1.15

analyses

1.14

analyse

1.13

Activations Density 0.087%

references to analysis and examination of data

No Comments

No Known Activations