INDEX

Explanations

mentions of the word "Warner" followed by a number

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.99

 habang

-0.78

 kapag

-0.69

resizeMode

-0.63

 hanggang

-0.61

 siyang

-0.57

 كومونز

-0.56

FetchType

-0.56

 tayo

-0.56

 niyang

-0.56

POSITIVE LOGITS

 Warner

1.46

Warner

1.32

 maksi

0.87

 heapq

0.87

 pank

0.85

WB

0.80

 Minang

0.78

wb

0.77

 Burbank

0.76

sml

0.74

Activations Density 0.436%

mentions of the word "Warner" followed by a number

No Comments

No Known Activations