INDEX

Explanations

terms related to systematic evaluations and oversight of programs or policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

MemoryWarning

-0.38

gl

-0.37

Ẫ

-0.36

BindView

-0.35

 Darwin

-0.35

str

-0.34

String

-0.34

juna

-0.34

gle

-0.33

stat

-0.33

POSITIVE LOGITS

setVerticalGroup

1.13

richTextPanel

0.85

LookAnd

0.79

TagMode

0.73

__':

0.73

 utafitiHapana

0.73

initComponents

0.72

 consultato

0.71

StructEnd

0.71

 setSelected

0.70

Activations Density 0.942%

terms related to systematic evaluations and oversight of programs or policies

No Comments

No Known Activations