INDEX

Explanations

XML or HTML syntax elements, particularly opening and closing tags

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

Code documentation summaries

np_acts-logits-general · gemini-2.0-flash

summarization

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

AsUp

-0.85

StoreMessageInfo

-0.63

oneofs

-0.60

ProcessEvent

-0.54

ThroughAttribute

-0.54

errHandler

-0.53

Попис

-0.52

 nakalista

-0.52

 AspNetCore

-0.51

LookAnd

-0.51

POSITIVE LOGITS

summary

1.54

 summary

1.50

 Summary

1.33

Summary

1.28

SUMMARY

1.13

 summaries

1.13

 SUMMARY

1.12

 summarized

1.04

 summarize

1.02

 summarizes

0.94

Activations Density 0.034%

XML or HTML syntax elements, particularly opening and closing tags

Code documentation summaries

summarization

No Comments

No Known Activations