INDEX

Explanations

sections labeled as summaries in programming or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

LookAnd

-1.16

 Houſe

-1.10

 doubtnut

-1.09

 itſelf

-1.06

 houſe

-1.00

 ſever

-1.00

 Reſ

-0.99

 ſind

-0.98

 Monfieur

-0.96

 poffe

-0.94

POSITIVE LOGITS

summary

2.20

 summary

1.04

Summary

1.00

 Summary

0.91

 SUMMARY

0.88

SUMMARY

0.82

sum

0.70

0.66

summ

0.66

sum

0.64

Activations Density 0.020%

sections labeled as summaries in programming or documentation

No Comments

No Known Activations