INDEX

Explanations

terms related to scientific research and academia

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

Text before citations or references

np_acts-logits-general · gemini-2.0-flash

scientific names and symbols

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

 ExecuteAsync

-0.80

utnik

-0.66

instantiate

-0.63

typeorm

-0.63

 statement

-0.58

nö

-0.58

GEBURTS

-0.55

 STATEMENT

-0.54

haupt

-0.54

odeon

-0.53

POSITIVE LOGITS

ting

0.76

 preocupes

0.71

 pleaſure

0.68

 themſelves

0.68

tttt

0.65

 ſeveral

0.63

 poffe

0.62

 dieß

0.62

 ſub

0.62

SOURCES

0.62

Activations Density 0.558%

terms related to scientific research and academia

Text before citations or references

scientific names and symbols

No Comments

No Known Activations