INDEX

Explanations

references to daily activities or routines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

RegressionTest

-0.84

tvguidetime

-0.83

__(/*!

-0.81

 StringTokenizer

-0.81

NameInMap

-0.81

 testator

-0.79

 geologists

-0.76

 boobs

-0.74

PerformLayout

-0.73

RuleContext

-0.73

POSITIVE LOGITS

 daily

3.42

daily

3.13

 Daily

3.10

Daily

3.00

 DAILY

2.89

DAILY

2.73

 täglichen

2.07

 täglich

1.99

 nightly

1.97

 weekly

1.96

Activations Density 0.045%

references to daily activities or routines

No Comments

No Known Activations