INDEX

Explanations

expressions of appreciation and acknowledgment in discussions

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

Follows second person pronouns or references

np_acts-logits-general · gemini-2.0-flash

valid points and agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 архивлан

-0.70

AnimationsModule

-0.63

+:+

-0.62

بوابة

-0.60

 referenties

-0.58

SourceChecksum

-0.58

 يتيمه

-0.58

zzleHttp

-0.57

 مشين

-0.56

 jemals

-0.56

POSITIVE LOGITS

 insightful

0.69

 perceptive

0.68

 points

0.60

 indeed

0.60

 suggestion

0.60

 astute

0.57

 Exactly

0.56

 effectivement

0.56

Indeed

0.55

 exactly

0.54

Activations Density 0.263%

expressions of appreciation and acknowledgment in discussions

Follows second person pronouns or references

valid points and agreement

No Comments

No Known Activations