INDEX

Explanations

instances where someone tells a secret or reveals information to others.

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

AtA

-0.75

 Domínguez

-0.71

nachron

-0.70

 gmbh

-0.70

 Penna

-0.70

TheGreat

-0.69

 volon

-0.69

 pamph

-0.68

 Haci

-0.67

 Méndez

-0.67

POSITIVE LOGITS

 what

0.73

how

0.70

 about

0.70

<bos>

0.69

 whether

0.60

why

0.59

what

0.57

about

0.56

know

0.56

GIVEREF

0.55

Activations Density 0.264%

instances where someone tells a secret or reveals information to others.

No Comments

No Known Activations