INDEX

Explanations

phrases and terms related to limitations or restrictions

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

 full

-0.54

setDo

-0.54

lay

-0.52

wój

-0.50

Lay

-0.50

his

-0.50

off

-0.48

lay

-0.48

瞰

-0.48

 GlobalKey

-0.46

POSITIVE LOGITS

 limitation

1.27

 restriction

1.10

 Limitation

1.10

InjectAttribute

1.08

 Restriction

1.04

MigrationBuilder

1.00

OGND

0.95

Lim

0.93

restriction

0.93

limit

0.93

Activations Density 0.154%

phrases and terms related to limitations or restrictions

No Comments

No Known Activations