INDEX

Explanations

phrases that question or contemplate events and scenarios regarding outcomes and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 avoient

-0.58

 serem

-0.58

 fortfarande

-0.58

 livré

-0.54

 PATENT

-0.54

LookAnd

-0.52

styleable

-0.52

 cérami

-0.51

 suspendu

-0.51

itorious

-0.51

POSITIVE LOGITS

 initComponents

0.76

InstanceState

0.71

URLException

0.71

UserScript

0.71

(||

0.68

GetAxis

0.67

HostException

0.67

Demografia

0.67

utenants

0.66

 الحره

0.63

Activations Density 0.125%

phrases that question or contemplate events and scenarios regarding outcomes and consequences

No Comments

No Known Activations