INDEX

Explanations

elements related to expressions of gratitude or appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

AddTagHelper

-0.57

unhofer

-0.54

 excru

-0.53

ConstraintMaker

-0.51

 ProtoMessage

-0.50

بوابة

-0.49

vrons

-0.49

OCCURRED

-0.48

mybatisplus

-0.48

://

-0.47

POSITIVE LOGITS

 behaviour

0.80

️

0.79

 Behaviour

0.77

 BEHAV

0.71

Behaviour

0.71

Nice

0.70

 hygiene

0.70

 hygienic

0.70

 👌

0.70

 cooperative

0.69

Activations Density 0.028%

elements related to expressions of gratitude or appreciation

No Comments

No Known Activations