INDEX

Explanations

names related to individuals and locations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 snippetHide

-0.56

InsertCommand

-0.54

 ComVisible

-0.49

 Kurs

-0.47

dflare

-0.46

 jLabel

-0.46

 dest

-0.46

NKC

-0.46

onics

-0.45

ontin

-0.45

POSITIVE LOGITS

yama

1.14

 affor

0.85

 quoique

0.83

 chery

0.80

 montrant

0.80

 excu

0.78

ross

0.78

 auxquelles

0.77

 Traité

0.76

 AppBundle

0.74

Activations Density 0.577%

names related to individuals and locations

No Comments

No Known Activations