INDEX

Explanations

references to organizations, political events, and actions

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

fordable

-0.63

 intersper

-0.62

 disreg

-0.60

 downvotes

-0.59

 lorenzo

-0.59

hmmmm

-0.59

 javier

-0.58

 impra

-0.57

 encomp

-0.57

 eyel

-0.57

POSITIVE LOGITS

 akut

0.58

because

0.57

 antik

0.55

 because

0.55

 optik

0.55

unless

0.54

 altogether

0.52

DataSnapshot

0.52

Pozdrawiam

0.52

ModelForm

0.51

Activations Density 0.662%

references to organizations, political events, and actions

No Comments

No Known Activations