INDEX

Explanations

actions and observations related to looking and gaze

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 haremos

-0.33

Carriera

-0.33

 Karriere

-0.32

 Behaup

-0.29

 ridurre

-0.29

 geçir

-0.29

 raça

-0.28

Insurance

-0.28

 kalın

-0.28

 loops

-0.28

POSITIVE LOGITS

verwijspagina

0.70

InjectAttribute

0.63

抬头

0.57

rungsseite

0.57

回头

0.57

抬起头

0.56

 CURIAM

0.55

ⓧ

0.55

RTRS

0.55

FormTagHelper

0.54

Activations Density 0.213%

actions and observations related to looking and gaze

No Comments

No Known Activations