INDEX

Explanations

parentheses and other related punctuation in code or markup

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ftet

-0.64

 Frick

-0.62

mat

-0.62

sch

-0.61

 Ritz

-0.61

 túi

-0.60

 rész

-0.58

Sn

-0.58

CRU

-0.58

 unut

-0.58

POSITIVE LOGITS

>(

1.62

>(_

1.05

>();

1.04

>(

1.02

>>(

1.01

>("

1.01

>();

1.00

[]>(

0.97

 poffible

0.95

>::

0.94

Activations Density 0.062%

parentheses and other related punctuation in code or markup

No Comments

No Known Activations