INDEX

Explanations

mentions related to broadcasting or publishing news articles

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.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

<bos>

-3.06

SourceChecksum

-0.89

webElementXpaths

-0.89

новништво

-0.79

LookAnd

-0.74

InjectAttribute

-0.71

MessageOf

-0.71

 ddelweddau

-0.70

 "..\..\..\

-0.70

ⓧ

-0.70

POSITIVE LOGITS

aen

1.59

 wien

1.58

mef

1.52

 effe

1.48

 squa

1.48

 stockholm

1.47

fta

1.44

 increa

1.42

 affor

1.41

fte

1.40

Activations Density 3.193%

mentions related to broadcasting or publishing news articles

No Comments

No Known Activations