INDEX

Explanations

mentions of specific locations or organizations in 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>

-3.47

ⓧ

-1.21

<?

-1.02

-1.01

/**

-0.97

/***

-0.94

/*

-0.82

<?

-0.76

 disbur

-0.73

USTAIN

-0.68

POSITIVE LOGITS

 Presenta

0.78

 véhic

0.75

 seksi

0.75

Juf

0.70

 Cerca

0.69

 expériment

0.68

 miniatura

0.68

 Contribu

0.67

 catég

0.67

 pleins

0.67

Activations Density 0.431%

mentions of specific locations or organizations in news articles

No Comments

No Known Activations