INDEX

Explanations

phrases indicating addition or concatenation in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

-0.55

енча

-0.53

 invece

-0.50

-0.49

Second

-0.47

sch

-0.46

[`

-0.45

 вдох

-0.44

bellar

-0.44

 flakes

-0.44

POSITIVE LOGITS

帖最后由

1.10

 nahilalakip

1.06

posedge

0.97

">'+

0.97

MigrationBuilder

0.96

escaping

0.96

ագրություններ

0.95

__*/

0.87

"):

0.86

complexContent

0.85

Activations Density 0.019%

phrases indicating addition or concatenation in programming contexts

No Comments

No Known Activations