INDEX

Explanations

references to specific locations or entities, specifically related to legal matters or law enforcement

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

 depic

-0.58

 McKee

-0.57

 poetical

-0.56

 memberId

-0.53

 salutary

-0.53

 eventId

-0.53

 groupName

-0.52

 Beal

-0.52

 vainly

-0.51

 loue

-0.51

POSITIVE LOGITS

 Newton

1.09

Newton

1.04

newton

0.87

 newton

0.83

 NEWTON

0.76

 Brow

0.73

 Newt

0.71

 Newtown

0.71

Brow

0.64

 inay

0.63

Activations Density 0.694%

references to specific locations or entities, specifically related to legal matters or law enforcement

No Comments

No Known Activations