INDEX

Explanations

code-related terms and references, specifically related to templates and standard input/output libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

thood

-0.51

 ModelExpression

-0.50

 كومونز

-0.49

defer

-0.48

apin

-0.47

 said

-0.45

tft

-0.45

rington

-0.44

dom

-0.44

 mentioned

-0.43

POSITIVE LOGITS

nullable

1.40

:✨

1.21

ResumeLayout

1.11

mybatisplus

0.94

 صوتيه

0.92

stateProvider

0.92

Tikang

0.88

migrationBuilder

0.86

templateUrl

0.85

PerformLayout

0.81

Activations Density 0.016%

code-related terms and references, specifically related to templates and standard input/output libraries

No Comments

No Known Activations