INDEX

Explanations

terms related to cognitive abilities and tasks

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

 Darío

-0.55

 philanth

-0.54

 philo

-0.54

 Valentín

-0.52

 incarcer

-0.52

Cormack

-0.51

 dramatist

-0.50

 ritratto

-0.50

 Alcalde

-0.50

 pamph

-0.49

POSITIVE LOGITS

 cognitive

1.14

 Cognitive

1.08

Cognitive

1.05

cognitive

0.99

 cognition

0.82

nitive

0.81

Cog

0.75

 cogni

0.73

Cog

0.72

kog

0.70

Activations Density 0.084%

terms related to cognitive abilities and tasks

No Comments

No Known Activations