INDEX

Explanations

medicine or health-related terms, especially related to mental health and psychiatry

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>

-2.74

 CreateTagHelper

-0.77

CPtr

-0.69

MessageOf

-0.67

JspWriter

-0.66

TagHelpers

-0.65

ുറ

-0.63

Descripció

-0.61

ViewFeatures

-0.60

}{@

-0.59

POSITIVE LOGITS

 ecru

1.66

 tolerably

1.55

 swarovski

1.55

 unwarran

1.51

 increa

1.48

 disagre

1.47

 matel

1.44

 hairc

1.44

 Manufact

1.44

 maneu

1.44

Activations Density 0.517%

medicine or health-related terms, especially related to mental health and psychiatry

No Comments

No Known Activations