INDEX

Explanations

assertions related to expected outcomes in testing

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

tagHelperRunner

-0.97

rungsseite

-0.90

bootstrapcdn

-0.85

 Chwiliwch

-0.84

 ſche

-0.79

੝

-0.79

odeon

-0.77

 سكانية

-0.75

الحياه

-0.73

URLException

-0.73

POSITIVE LOGITS

toBe

1.51

be

0.59

ToBe

0.56

be

0.49

Be

0.48

Be

0.44

 less

0.42

non

0.40

BE

0.39

 shouldBe

0.39

Activations Density 0.004%

assertions related to expected outcomes in testing

No Comments

No Known Activations