INDEX

Explanations

terms related to "targets" and their associated properties in a coding or technical context

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

 dysplasia

-0.71

CBA

-0.70

Jaz

-0.66

xffffff

-0.65

 fistula

-0.62

CBA

-0.62

 colitis

-0.61

 FLOW

-0.60

 papyrus

-0.57

 psycopg

-0.56

POSITIVE LOGITS

 targets

1.78

 TARGET

1.64

 Target

1.61

 Targets

1.60

 target

1.58

TARGET

1.57

targets

1.50

Target

1.44

target

1.40

 getTarget

1.40

Activations Density 0.080%

terms related to "targets" and their associated properties in a coding or technical context

No Comments

No Known Activations