INDEX

Explanations

positive feedback and recommendations in product reviews

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>

-1.92

public

-0.78

-0.69

-0.67

 manage

-0.66

-0.65

formik

-0.65

-0.64

POSITIVE LOGITS

 reluct

2.13

 impra

2.10

 maneu

2.07

 affor

2.02

 accla

2.01

 disagre

1.97

 fortn

1.90

 inev

1.90

 depic

1.87

 increa

1.84

Activations Density 0.994%

positive feedback and recommendations in product reviews

No Comments

No Known Activations