INDEX

Explanations

items related to conflict or aggression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 يتيمه

-0.61

SourceChecksum

-0.58

CodedInputStream

-0.55

BindView

-0.53

WebServlet

-0.52

edata

-0.51

/#

-0.51

 PLWABN

-0.50

 بيها

-0.50

Искәрмәләр

-0.49

POSITIVE LOGITS

 stuck

0.77

 taped

0.72

 dangling

0.71

 attached

0.71

 strapped

0.66

 clutched

0.66

 balanced

0.64

 clamped

0.64

 affixed

0.64

 tied

0.63

Activations Density 0.548%

items related to conflict or aggression

No Comments

No Known Activations