INDEX

Explanations

terms related to citations and references

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

"reference" or "references"

np_acts-logits-general · gemini-2.0-flash

reference / references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

chastic

-0.54

enumii

-0.54

GenerationType

-0.53

asymp

-0.52

UserScript

-0.52

Gut

-0.51

Celeste

-0.51

enumi

-0.50

хьтан

-0.50

 Himo

-0.50

POSITIVE LOGITS

 reference

1.34

 references

1.19

 Reference

1.13

reference

1.13

Reference

1.07

 REFERENCE

1.05

 refer

1.03

 References

1.01

 référence

0.98

 REFER

0.96

Activations Density 0.374%

terms related to citations and references

"reference" or "references"

reference / references

No Comments

No Known Activations