INDEX

Explanations

multiple occurrences of the word "right" 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 @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 témo

-0.64

Personensuche

-0.64

 rendent

-0.58

seits

-0.57

 Audiodateien

-0.57

 adjourn

-0.57

GetAsync

-0.56

officer

-0.55

 rotors

-0.54

IGraphics

-0.54

POSITIVE LOGITS

 appropriate

0.94

 proper

0.84

 suited

0.79

 suitable

0.78

 Wrong

0.77

 rätt

0.77

+"/"+

0.77

 wrong

0.76

Appropriate

0.75

榄

0.74

Activations Density 0.019%

multiple occurrences of the word "right" in various contexts

No Comments

No Known Activations