INDEX

Explanations

the occurrence of the word "Rep" and associated variations indicating representatives or their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 صوتيه

-0.68

FormTagHelper

-0.60

extAlignment

-0.58

 onPostExecute

-0.58

ftagPool

-0.56

Cyfeiriadau

-0.55

quelize

-0.51

روز

-0.49

isseurs

-0.49

ตู

-0.48

POSITIVE LOGITS

 собой

0.72

 payee

0.64

tvguidetime

0.61

ativeness

0.60

󠁢

0.57

ngrx

0.56

 linkovi

0.56

 AssemblyCulture

0.55

InsertCommand

0.52

Lesen

0.51

Activations Density 0.231%

the occurrence of the word "Rep" and associated variations indicating representatives or their actions

No Comments

No Known Activations