INDEX

Explanations

words associated with negativity or discontent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Tril

-0.52

cedure

-0.52

heder

-0.51

memcpy

-0.50

abadi

-0.49

 "..\..\

-0.48

Renato

-0.48

ânt

-0.47

ölker

-0.47

 الدولى

-0.47

POSITIVE LOGITS

setVerticalGroup

0.83

 lenker

0.68

 gynhyrchwyd

0.61

XtraGrid

0.61

 дописавши

0.60

 AssemblyCulture

0.59

 <=",

0.58

 fVar

0.58

elemField

0.57

הערות

0.56

Activations Density 0.073%

words associated with negativity or discontent

No Comments

No Known Activations