INDEX

Explanations

specific roles, professions, and related terminology in a conversational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 tartalomajánló

-0.58

MethodManager

-0.53

RegressionTest

-0.45

 يتيمه

-0.43

bootstrapcdn

-0.43

CppMethod

-0.42

#+#

-0.42

Spoljašnje

-0.41

󠁧

-0.40

 Infórmanos

-0.40

POSITIVE LOGITS

 kasarigan

0.52

ніципалі

0.49

HasAnnotation

0.44

EndGlobalSection

0.44

 مُعرِّف

0.44

 shitty

0.40

 bullshit

0.40

 noDo

0.40

 greasy

0.39

 crap

0.39

Activations Density 0.174%

specific roles, professions, and related terminology in a conversational context

No Comments

No Known Activations