INDEX

Explanations

expressions related to comparison and evaluation of qualities or attributes

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

 doPost

-0.56

 FixedUpdate

-0.53

 stagione

-0.53

autogui

-0.52

læ

-0.52

 محفوظة

-0.51

 CGSize

-0.50

mapbox

-0.50

 ferons

-0.49

roleId

-0.49

POSITIVE LOGITS

 understatement

0.58

 unimaginable

0.58

lative

0.53

protoimpl

0.53

 intensity

0.53

URLException

0.53

 unbelievable

0.52

 further

0.51

ünster

0.51

Expectations

0.51

Activations Density 0.240%

expressions related to comparison and evaluation of qualities or attributes

No Comments

No Known Activations