INDEX

Explanations

phrases related to chronological events or sequences

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MET

-0.50

 Även

-0.48

Ro

-0.47

Cho

-0.47

Bra

-0.47

Bra

-0.47

Ra

-0.46

Asimismo

-0.46

UObject

-0.46

letter

-0.45

POSITIVE LOGITS

 SINCE

1.01

 bordeaux

0.90

 affez

0.85

 unce

0.85

 poichè

0.85

 ecru

0.83

 ciga

0.83

 cannes

0.82

 encomp

0.82

 shenan

0.81

Activations Density 0.074%

phrases related to chronological events or sequences

No Comments

No Known Activations