INDEX

Explanations

mathematical expressions and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Id

-1.07

Is

-1.06

-1.01

IS

-0.89

Im

-0.88

Id

-0.87

Is

-0.87

Ｉ

-0.86

ID

-0.86

POSITIVE LOGITS

:+:

0.50

in

0.47

il

0.47

kkende

0.47

openzeppelin

0.46

SBATCH

0.45

tagHelperRunner

0.44

ii

0.43

ilog

0.43

iu

0.43

Activations Density 0.552%

mathematical expressions and notations

No Comments

No Known Activations