INDEX

Explanations

phrases indicating representation or action taken on someone's behalf

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 sample

-0.60

 natural

-0.57

 Grant

-0.55

 losing

-0.54

 disambiguazione

-0.53

言うと

-0.52

 choice

-0.51

 fast

-0.50

kfree

-0.49

 quên

-0.49

POSITIVE LOGITS

LEncoder

0.86

 оригіналу

0.86

WebControls

0.84

VersionUID

0.82

resave

0.78

 EnglishChoose

0.76

consulté

0.76

CrossRef

0.76

ClientSize

0.75

 wireType

0.73

Activations Density 0.101%

phrases indicating representation or action taken on someone's behalf

No Comments

No Known Activations