INDEX

Explanations

repeated mentions of "week" and related terms indicating the time period

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ISI

-0.79

<em>

-0.69

$>$

-0.68

 Salisbury

-0.68

bolista

-0.68

boutin

-0.67

 Kombat

-0.67

isbury

-0.67

ibatis

-0.66

umman

-0.66

POSITIVE LOGITS

 week

1.72

 WEEK

1.62

 Weeks

1.61

 weeks

1.61

 Week

1.54

week

1.52

WEEK

1.51

weeks

1.51

Week

1.44

 WEEKS

1.44

Activations Density 0.077%

repeated mentions of "week" and related terms indicating the time period

No Comments

No Known Activations