INDEX

Explanations

terms related to ranking or order

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

PLW

-0.72

ITTEN

-0.70

 aceptas

-0.67

coaster

-0.67

_('

-0.66

 Nusa

-0.65

Closer

-0.64

fores

-0.64

 useCallback

-0.64

feira

-0.64

POSITIVE LOGITS

 rank

2.27

 RANK

2.27

 Rank

2.19

 ranks

2.19

Rank

2.13

rank

2.11

 ranking

2.06

 Ranks

2.03

RANK

2.00

ranks

1.89

Activations Density 0.062%

terms related to ranking or order

No Comments

No Known Activations