INDEX

Explanations

code-related keywords and structures indicative of programming functions and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 للمعارف

-0.56

_$

-0.49

TestingModule

-0.48

דר

-0.48

getMinutes

-0.48

rebbero

-0.47

 rép

-0.46

⎨

-0.46

ocas

-0.45

мін

-0.44

POSITIVE LOGITS

 بلکه

0.65

 sondern

0.63

 else

0.62

':'

0.62

InjectAttribute

0.61

 Normdatei

0.60

saraba

0.59

 hanem

0.58

:''

0.56

жели

0.55

Activations Density 0.109%

code-related keywords and structures indicative of programming functions and data handling

No Comments

No Known Activations