INDEX

Explanations

descriptions of decisions and considerations made 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

 swarovski

-1.17

 actionTypes

-1.15

 sappi

-1.13

 unlaw

-1.11

 embodi

-1.08

 squa

-1.07

 hairc

-1.07

 pylab

-1.06

 lamborghini

-1.06

 bourgeo

-1.05

POSITIVE LOGITS

 wanted

1.13

 decided

0.99

 couldn

0.88

 needed

0.87

wanted

0.83

 wasn

0.79

 chose

0.78

 felt

0.77

 didn

0.77

 want

0.75

Activations Density 0.362%

descriptions of decisions and considerations made in a process

No Comments

No Known Activations