INDEX

Explanations

the letter 'e' in various contexts

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

setVerticalGroup

-0.67

GEBURTSDATUM

-0.60

 Broder

-0.53

ulity

-0.52

TagMode

-0.51

]='\

-0.51

GLUT

-0.50

hema

-0.47

AFTA

-0.47

 Verf

-0.47

POSITIVE LOGITS

enumi

0.61

isSuccessful

0.61

SupportActionBar

0.60

={`/

0.60

ましい

0.60

 scattata

0.58

lielmo

0.58

UrlResolution

0.57

HomeAsUpEnabled

0.57

раздо

0.55

Activations Density 0.041%

the letter 'e' in various contexts

No Comments

No Known Activations