INDEX

Explanations

names and terms associated with academic or scientific references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 nakalista

-1.04

keyframes

-0.81

 Kine

-0.71

hari

-0.68

Tracce

-0.67

 konusu

-0.67

yid

-0.67

pax

-0.66

pax

-0.66

 Paine

-0.66

POSITIVE LOGITS

wsz

0.84

 Kapp

0.77

Alc

0.76

 dimenti

0.75

 anisotropic

0.75

 Hermans

0.75

 øns

0.74

 Stans

0.73

Pem

0.73

̈́

0.72

Activations Density 2.289%

names and terms associated with academic or scientific references

No Comments

No Known Activations