INDEX

Explanations

descriptions of physical actions and locations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kram

-0.93

 makro

-0.93

 stoff

-0.85

uhr

-0.84

 minimalis

-0.84

 traktor

-0.81

 alkoh

-0.81

 maksi

-0.80

 katal

-0.79

 kras

-0.78

POSITIVE LOGITS

 heights

0.74

 Heights

0.69

 height

0.68

 rooftop

0.68

 climbing

0.67

 climbed

0.66

 atop

0.66

 getHeight

0.65

 perched

0.65

 suspended

0.62

Activations Density 0.396%

descriptions of physical actions and locations

No Comments

No Known Activations