INDEX

Explanations

mentions of unspecified or vague situations or issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Datuak

-0.67

AutoScaleMode

-0.62

IntoConstraints

-0.62

ことは

-0.56

 jakie

-0.52

mtrl

-0.49

Dữ

-0.49

Jop

-0.49

LookAnd

-0.47

μβρίου

-0.46

POSITIVE LOGITS

 else

1.26

Else

0.92

 akin

0.83

igshid

0.80

Somewhere

0.80

else

0.79

somewhere

0.79

 Else

0.78

 ELSE

0.77

 somewhere

0.76

Activations Density 0.067%

mentions of unspecified or vague situations or issues

No Comments

No Known Activations