INDEX

Explanations

details and information related to legal cases and political figures

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

 Ename

-1.11

 unspeak

-0.99

Wtf

-0.94

 embodi

-0.93

 indestru

-0.93

Mmm

-0.92

 liberality

-0.91

 disreg

-0.90

 poetical

-0.89

 shenan

-0.89

POSITIVE LOGITS

ì

0.56

 Bourgoin

0.54

 lenker

0.53

+#+#

0.52

İstinadlar

0.52

 kayo

0.51

 stránka

0.49

 consegna

0.48

›

0.48

 estrema

0.48

Activations Density 1.619%

details and information related to legal cases and political figures

No Comments

No Known Activations