INDEX

Explanations

phrases and references related to social interactions and personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

ⓘ

-0.59

Билгалдахарш

-0.58

 Inſ

-0.57

IntoConstraints

-0.56

TagMode

-0.56

 juſ

-0.55

曖昧さ回避

-0.52

AutoScaleMode

-0.50

Jegyzetek

-0.50

########.

-0.47

POSITIVE LOGITS

 pelbagai

0.52

 bahawa

0.49

 kerana

0.48

 Kristian

0.48

 sahaja

0.48

initialise

0.44

 Merv

0.44

 iaitu

0.43

 bahagian

0.42

 lorry

0.41

Activations Density 0.041%

phrases and references related to social interactions and personal experiences

No Comments

No Known Activations