INDEX

Explanations

references to weeks and their duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

databind

-0.76

boutin

-0.72

isbury

-0.71

ISI

-0.71

<em>

-0.70

gegeven

-0.70

$>$

-0.69

 للاسماء

-0.69

 Salisbury

-0.67

insa

-0.65

POSITIVE LOGITS

 week

1.92

 WEEK

1.80

 Week

1.74

 Weeks

1.69

 weeks

1.68

week

1.68

WEEK

1.66

Week

1.65

weeks

1.53

 WEEKS

1.48

Activations Density 0.064%

references to weeks and their duration

No Comments

No Known Activations