INDEX

Explanations

indicators of statistical data and comparisons

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

-0.85

-0.78

and

-0.77

-0.74

$\

-0.72

-0.71

in

-0.70

di

-0.70

or

-0.67

en

-0.67

POSITIVE LOGITS

 itſelf

1.49

ſelf

1.47

Efq

1.47

ſelves

1.45

 myſelf

1.44

 purpoſe

1.36

 Majefty

1.36

 Jefus

1.35

 ſeveral

1.33

 Reſ

1.31

Activations Density 0.450%

indicators of statistical data and comparisons

No Comments

No Known Activations