INDEX

Explanations

signals related to measurement or evaluation in various contexts

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

 sights

-0.61

 Cama

-0.59

ネマ

-0.58

 Brod

-0.58

 ayak

-0.57

 laughs

-0.56

 Findlay

-0.56

ärna

-0.55

vau

-0.54

zuki

-0.54

POSITIVE LOGITS

BufferException

0.79

omiast

0.69

 mergeFrom

0.68

 виправивши

0.64

кож

0.62

umumkan

0.61

uxxxx

0.61

 ProtoMessage

0.61

 مشين

0.60

 समीक्षक

0.60

Activations Density 0.261%

signals related to measurement or evaluation in various contexts

No Comments

No Known Activations