INDEX

Explanations

instances of reported speech or statements made by individuals

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

Attribution via "said"

np_acts-logits-general · gemini-2.0-flash

reporting speech

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 '\\;'

-0.95

 AssemblyCulture

-0.92

 CreateTagHelper

-0.87

 transfieras

-0.84

AddTagHelper

-0.84

EndGlobalSection

-0.78

 EconPapers

-0.77

 betweenstory

-0.70

principalTable

-0.69

 Monfieur

-0.67

POSITIVE LOGITS

 referencing

0.72

 referring

0.72

 <<<<<<<<<<<<<<

0.63

 jokingly

0.53

 nodding

0.53

refer

0.52

0.51

 apologe

0.49

wry

0.49

 succinctly

0.49

Activations Density 0.041%

instances of reported speech or statements made by individuals

Attribution via "said"

reporting speech

No Comments

No Known Activations