INDEX

Explanations

references to "target" in various contexts

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

"target" followed by related words

np_acts-logits-general · gemini-2.0-flash

target

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 noqa

-0.67

<![

-0.59

viewDidLoad

-0.59

reszcie

-0.58

 tslint

-0.57

 fistula

-0.55

 científica

-0.55

 dysplasia

-0.54

 colitis

-0.53

 vestibular

-0.52

POSITIVE LOGITS

 targets

1.24

targets

1.12

 Targets

1.08

 target

1.02

 Target

1.01

TARGET

1.00

 TARGET

0.99

Targets

0.98

 getTarget

0.97

="_

0.93

Activations Density 0.076%

references to "target" in various contexts

"target" followed by related words

target

No Comments

No Known Activations