INDEX

Explanations

phrases indicating possession or ownership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

<bos>

-0.48

pro

-0.39

order

-0.38

pro

-0.37

stra

-0.36

malla

-0.36

AccessorTable

-0.36

ru

-0.36

per

-0.36

wij

-0.35

POSITIVE LOGITS

 there

1.08

MessageTagHelper

0.87

there

0.85

AndEndTag

0.82

 THERE

0.77

 linkovi

0.77

 ehre

0.76

MigrationBuilder

0.76

THERE

0.75

TagHelper

0.74

Activations Density 0.095%

phrases indicating possession or ownership

No Comments

No Known Activations