INDEX

Explanations

keywords and phrases related to focus and attention in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

NewGuid

-0.44

 borbo

-0.38

Mui

-0.36

 prét

-0.35

 meyd

-0.35

 AspNetCore

-0.34

ndose

-0.34

 namanya

-0.34

 pommes

-0.34

 CallOverrides

-0.34

POSITIVE LOGITS

 placed

0.67

 shifted

0.64

 directed

0.61

 diverted

0.60

 focussed

0.59

placed

0.59

 squarely

0.56

 focused

0.55

 Placed

0.54

 centred

0.51

Activations Density 0.249%

keywords and phrases related to focus and attention in various contexts

No Comments

No Known Activations