INDEX

Explanations

past tense verbs and phrases indicating actions or events that have occurred

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 صوتيه

-0.81

ReusableCell

-0.79

 démocr

-0.77

inSlope

-0.76

 kasarigan

-0.75

 متعلقه

-0.74

woordig

-0.73

 ddelweddau

-0.73

addCriterion

-0.73

PreferredItem

-0.73

POSITIVE LOGITS

 earlier

0.98

 previously

0.82

 previous

0.79

 hadn

0.75

Earlier

0.74

 Earlier

0.74

earlier

0.73

had

0.71

previous

0.67

 hoped

0.66

Activations Density 0.254%

past tense verbs and phrases indicating actions or events that have occurred

No Comments

No Known Activations