INDEX

Explanations

negations and conditional statements related to expectations or clarifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

RTLR

-0.67

 EconPapers

-0.67

AutoScaleMode

-0.56

__*/

-0.49

ंदीखरीदारी

-0.49

Atoi

-0.47

CIL

-0.47

homonymie

-0.45

tvguidetime

-0.45

fromJson

-0.44

POSITIVE LOGITS

to

0.86

 decir

0.64

 сказать

0.59

to

0.57

To

0.56

To

0.55

 говоря

0.54

say

0.52

 mencionar

0.47

 dizer

0.45

Activations Density 0.282%

negations and conditional statements related to expectations or clarifications

No Comments

No Known Activations

negations and conditional statements related to expectations or clarifications

No Comments

No Known Activations