INDEX

Explanations

phrases indicating the presence or concern of danger or negative circumstances

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

Follows "there" and a form of "to be"

np_acts-logits-general · gemini-2.0-flash

there are/were existence statements

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

 stuff

-0.96

 verksamhet

-0.84

 legislation

-0.84

stuff

-0.77

 Stuff

-0.74

Stuff

-0.74

 evidence

-0.74

 advice

-0.71

 STUFF

-0.70

 aktivitet

-0.69

POSITIVE LOGITS

 يتيمه

0.91

 kasarigan

0.90

Autoritní

0.88

 CreateTagHelper

0.87

AddTagHelper

0.86

 mergeFrom

0.83

رشف

0.81

VIAF

0.80

GraphicsUnit

0.79

MemoryWarning

0.78

Activations Density 0.480%

phrases indicating the presence or concern of danger or negative circumstances

Follows "there" and a form of "to be"

there are/were existence statements

No Comments

No Known Activations