INDEX

Explanations

references to specific names or entities, possibly related to an investigative or journalistic context

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

 McLaugh

-0.78

 Joaqu

-0.76

 Rued

-0.72

>\<

-0.72

 cias

-0.71

 McInt

-0.71

 Keny

-0.71

 Gorb

-0.70

 Rine

-0.70

 reluct

-0.69

POSITIVE LOGITS

it

0.68

来说

0.64

 there

0.59

而言

0.57

來說

0.52

 this

0.49

there

0.48

who

0.47

 это

0.47

 anyway

0.46

Activations Density 0.211%

references to specific names or entities, possibly related to an investigative or journalistic context

No Comments

No Known Activations