INDEX

Explanations

instructions or steps in a process

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

 Khart

-1.13

 Keny

-1.06

Juf

-1.03

 Abbé

-1.03

 maneu

-1.00

 emphat

-1.00

 Minang

-0.96

Hæ

-0.96

 volunte

-0.96

 depic

-0.94

POSITIVE LOGITS

 easy

0.75

 effortless

0.73

 easier

0.72

 simply

0.72

 simplicity

0.71

 simpler

0.70

bersicht

0.69

easy

0.69

 effortlessly

0.69

 easily

0.68

Activations Density 0.408%

instructions or steps in a process

No Comments

No Known Activations