INDEX

Explanations

references to the term "Cal" or similar variations, indicating a focus on a specific entity or subject associated with that term

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

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

 تانيه

-0.85

thâu

-0.81

RenderAtEndOf

-0.73

bukkit

-0.66

iqué

-0.64

hatsu

-0.64

 itſelf

-0.64

 disambiguazione

-0.62

idoscope

-0.61

 pleaſure

-0.57

POSITIVE LOGITS

🏼

0.59

 Signalez

0.54

🏽

0.50

🏾

0.49

🏻

0.49

span

0.48

воз

0.47

 liitty

0.47

 ControllerBase

0.47

𝘃

0.45

Activations Density 0.080%

references to the term "Cal" or similar variations, indicating a focus on a specific entity or subject associated with that term

No Comments

No Known Activations