INDEX

Explanations

phrases indicating slight or minor changes in conditions or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

醐

-0.33

sprozess

-0.33

 Gestaltung

-0.31

 Construcción

-0.31

VolleyError

-0.31

 kalın

-0.31

tská

-0.30

 enfrent

-0.30

 kurulan

-0.29

 Pembangunan

-0.29

POSITIVE LOGITS

 slight

1.08

 Slight

0.91

 briefly

0.90

Slight

0.90

Brief

0.85

 brief

0.82

mild

0.82

 Slightly

0.81

 slightly

0.80

slightly

0.80

Activations Density 0.767%

phrases indicating slight or minor changes in conditions or attributes

No Comments

No Known Activations