INDEX

Explanations

references to targets in a programming or computational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

 dysplasia

-0.80

CBA

-0.76

CBA

-0.71

 fistula

-0.70

Jaz

-0.67

 colitis

-0.65

thâu

-0.65

 ProgressDialog

-0.65

 psycopg

-0.64

PMA

-0.64

POSITIVE LOGITS

 targets

1.60

 TARGET

1.48

 Target

1.43

 target

1.42

 Targets

1.41

TARGET

1.39

targets

1.34

Target

1.26

target

1.25

 getTarget

1.22

Activations Density 0.057%

references to targets in a programming or computational context

No Comments

No Known Activations