INDEX

Explanations

sequences of phrases or clauses that discuss the act of saying or turning concepts into actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Datuak

-0.72

FailureListener

-0.69

PerformLayout

-0.66

unhofer

-0.65

AntiForgeryToken

-0.65

="@+

-0.62

 interessieren

-0.62

GeneratedCode

-0.61

 useRef

-0.61

 genommen

-0.60

POSITIVE LOGITS

 ways

0.98

way

0.89

Ways

0.87

 Ways

0.85

Way

0.80

方式

0.74

Way

0.74

 WAYS

0.73

WAY

0.73

ways

0.72

Activations Density 0.140%

sequences of phrases or clauses that discuss the act of saying or turning concepts into actions

No Comments

No Known Activations