INDEX

Explanations

references to a target or objectives within 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 @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

thâu

-0.81

 dysplasia

-0.79

Jaz

-0.78

 fistula

-0.77

 Philo

-0.74

PMA

-0.73

LayoutPanel

-0.73

 colitis

-0.71

 tslint

-0.71

CBA

-0.71

POSITIVE LOGITS

 targets

1.42

 target

1.32

 Target

1.25

 TARGET

1.23

 Targets

1.22

TARGET

1.20

targets

1.18

target

1.10

 getTarget

1.10

Target

1.09

Activations Density 0.110%

references to a target or objectives within various contexts

No Comments

No Known Activations