INDEX

Explanations

occurrences of the word "format" or related terms indicating specification of formats in structured data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCompany

-0.92

 CreateTagHelper

-0.92

AnchorTagHelper

-0.87

 newOwner

-0.87

 calculées

-0.86

($__

-0.81

onViewCreated

-0.80

 <=",

-0.80

Seeker

-0.79

FieldBuilder

-0.76

POSITIVE LOGITS

 FORMAT

2.01

 format

1.95

format

1.87

 Format

1.86

 formats

1.86

FORMAT

1.78

Format

1.78

 Formats

1.70

formats

1.65

Formats

1.55

Activations Density 0.048%

occurrences of the word "format" or related terms indicating specification of formats in structured data

No Comments

No Known Activations