INDEX

Explanations

references to reports and reporting actions

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

ANTAGES

-0.70

 onlyOwner

-0.69

makedirs

-0.64

endants

-0.64

cstdlib

-0.63

 للاسماء

-0.63

nestjs

-0.63

disambiguation

-0.60

uckles

-0.60

guna

-0.60

POSITIVE LOGITS

 reports

2.05

 Reports

2.02

 report

1.97

Report

1.93

 Report

1.92

Reports

1.91

 REPORT

1.90

reports

1.83

report

1.79

 REPORTS

1.77

Activations Density 0.077%

references to reports and reporting actions

No Comments

No Known Activations