INDEX

Explanations

negative descriptors and terms related to flaws or failures 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 @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

assertNotNull

-0.64

libft

-0.63

日閲覧

-0.63

 uninterrupted

-0.59

רח

-0.57

uteen

-0.55

Portail

-0.54

⎩

-0.53

redirects

-0.53

 doInBackground

-0.53

POSITIVE LOGITS

 mauvais

0.90

 improper

0.89

 poorly

0.88

 badly

0.87

 mauvaise

0.85

 poor

0.84

Poor

0.81

 faulty

0.80

 wrong

0.80

 worse

0.80

Activations Density 0.986%

negative descriptors and terms related to flaws or failures in various contexts

No Comments

No Known Activations