INDEX

Explanations

mentions of specific brands or products

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

Scénario

-0.63

 devemos

-0.61

 vorrei

-0.59

 zví

-0.59

 poichè

-0.58

 occorre

-0.57

 dobbiamo

-0.56

 confira

-0.56

 esclusivamente

-0.55

randomUUID

-0.55

POSITIVE LOGITS

Hen

0.79

Hen

0.77

 Bens

0.72

Bem

0.71

Ot

0.70

 Mend

0.69

 Otter

0.68

 silikon

0.67

 Nadine

0.66

 Henne

0.66

Activations Density 0.665%

mentions of specific brands or products

No Comments

No Known Activations