INDEX

Explanations

references to legal and administrative filings

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>

-3.37

 Walkover

-0.76

WriteLiteral

-0.74

ⓧ

-0.67

CommonModule

-0.67

HasIndex

-0.67

↘

-0.66

//-----

-0.66

Pyx

-0.66

<td>

-0.65

POSITIVE LOGITS

 maneu

2.21

 affor

2.18

 impra

2.07

 increa

1.99

 emphat

1.97

 accla

1.97

 reluct

1.92

 disreg

1.90

 shenan

1.90

 uninten

1.86

Activations Density 0.073%

references to legal and administrative filings

No Comments

No Known Activations