INDEX

Explanations

instances of the term "case" in various contexts, often related to medical or legal scenarios

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mercurio

-1.07

 Monfieur

-1.06

 Theſe

-1.04

 pleaſure

-1.00

 raiſ

-0.98

 uſed

-0.95

Память

-0.93

edicated

-0.92

 havaianas

-0.91

 ſmall

-0.91

POSITIVE LOGITS

 cases

1.78

 case

1.65

 Cases

1.64

case

1.57

 CASE

1.57

 Case

1.56

Cases

1.54

cases

1.53

CASE

1.50

Case

1.47

Activations Density 0.112%

instances of the term "case" in various contexts, often related to medical or legal scenarios

No Comments

No Known Activations