INDEX

Explanations

terms and phrases related to statistical analysis and positions

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

starting with "pos"

np_acts-logits-general · gemini-2.0-flash

positions, posology, posthoc

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

Iden

-0.49

ty

-0.46

 surla

-0.45

wią

-0.44

 zweiter

-0.44

StringCopy

-0.44

 Europea

-0.44

 validate

-0.44

ALF

-0.43

TY

-0.43

POSITIVE LOGITS

 session

0.74

 '\\;'

0.72

SESSION

0.71

sessions

0.70

session

0.68

 SESSION

0.67

 Session

0.67

 sessions

0.66

LEncoder

0.62

sibilities

0.62

Activations Density 0.127%

terms and phrases related to statistical analysis and positions

starting with "pos"

positions, posology, posthoc

No Comments

No Known Activations