INDEX

Explanations

information related to actions taken by a person or organization

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

 sappi

-1.02

 purtroppo

-0.92

 vuol

-0.92

 vogli

-0.90

 migli

-0.90

 ideolog

-0.88

 persino

-0.86

 vorrei

-0.85

 chiaramente

-0.85

 specialmente

-0.85

POSITIVE LOGITS

by

0.67

 during

0.55

by

0.54

0.52

ted

0.51

 illegally

0.50

 together

0.50

 along

0.50

 without

0.50

Activations Density 0.445%

information related to actions taken by a person or organization

No Comments

No Known Activations