INDEX

Explanations

instances of the word "look" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 comigo

-0.72

protoimpl

-0.72

ptest

-0.63

 argint

-0.62

initComponents

-0.62

êmica

-0.61

 myndig

-0.61

nhà

-0.60

 CoreData

-0.59

vención

-0.59

POSITIVE LOGITS

 Looks

1.93

Looks

1.87

 looks

1.72

looks

1.59

 looked

1.55

 LOOKS

1.53

looked

1.32

 Looked

1.30

 stared

1.03

 stares

0.99

Activations Density 0.097%

instances of the word "look" and its variations

No Comments

No Known Activations