INDEX

Explanations

phrases indicating personal experiences and feelings related to coding and problem-solving

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

leyeb

-0.48

ahr

-0.47

figsize

-0.47

 ujednoznacz

-0.47

žev

-0.46

!*\

-0.44

/\.

-0.44

iertes

-0.43

mazioni

-0.43

indd

-0.43

POSITIVE LOGITS

 currently

3.77

currently

3.42

 Currently

3.30

Currently

3.23

 presently

3.16

 current

3.05

 CURRENT

2.85

 actuellement

2.77

current

2.76

 attualmente

2.72

Activations Density 1.099%

phrases indicating personal experiences and feelings related to coding and problem-solving

No Comments

No Known Activations