INDEX

Explanations

clothing and protective gear

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

__*/

-0.69

MergeFrom

-0.61

writeFieldEnd

-0.61

Aktualisiert

-0.59

tahui

-0.57

kreises

-0.57

 onCancelled

-0.55

 ſmall

-0.54

RTEE

-0.54

rollment

-0.53

POSITIVE LOGITS

 helmet

1.00

 jacket

0.95

 gloves

0.95

 Gloves

0.90

 Jacket

0.88

 Helmet

0.88

Shoes

0.88

 helmets

0.84

 shoes

0.83

 Shoes

0.83

Activations Density 0.225%

clothing and protective gear

No Comments

No Known Activations