INDEX

Explanations

dates, particularly focusing on the month of September across 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

InitStruct

-0.59

 Couture

-0.58

 Wohl

-0.57

osoba

-0.57

Outfit

-0.56

itness

-0.55

kháu

-0.55

onOptions

-0.55

ъек

-0.55

такт

-0.54

POSITIVE LOGITS

 September

2.92

September

2.60

 December

2.40

 April

2.22

 August

2.20

 November

2.19

December

2.12

 July

2.06

 January

2.04

 February

2.04

Activations Density 0.102%

dates, particularly focusing on the month of September across various contexts

No Comments

No Known Activations