INDEX

Explanations

mentions of statistic-related terms such as averages, populations, age, and prices

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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

html

-0.70

новништво

-0.69

BASELINE

-0.69

/**

-0.67

public

-0.66

cshtml

-0.66

cline

-0.66

 않는

-0.64

แล

-0.64

<bos>

-0.64

POSITIVE LOGITS

 emphat

2.06

 affor

1.97

 impra

1.94

 increa

1.92

 maneu

1.92

 strick

1.89

 accla

1.87

 unden

1.86

 squa

1.85

 reluct

1.84

Activations Density 0.192%

mentions of statistic-related terms such as averages, populations, age, and prices

No Comments

No Known Activations