INDEX

Explanations

names and specific scientific terms or 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

 Farley

-0.72

Mad

-0.69

Mur

-0.65

 coper

-0.62

nsec

-0.62

Big

-0.61

The

-0.61

Ten

-0.60

к

-0.59

POSITIVE LOGITS

 myſelf

1.04

ValueStyle

1.03

 ModelExpression

0.98

 Majefty

0.92

IsContent

0.91

RenderAtEndOf

0.91

 cauſe

0.87

 lemmas

0.87

 itſelf

0.86

 caufe

0.86

Activations Density 2.919%

names and specific scientific terms or references

No Comments

No Known Activations