INDEX

Explanations

technical terms and brand/product names related to dietary supplements and health-related products

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

<bos>

-2.06

พัน

-0.68

ValueGenerated

-0.67

-0.65

重

-0.65

do

-0.65

lang

-0.64

public

-0.64

ียม

-0.63

POSITIVE LOGITS

 stockholm

1.97

 maneu

1.89

 reluct

1.88

 milf

1.86

 shenan

1.85

 fortn

1.75

 depic

1.75

 accla

1.72

 strick

1.71

 scrat

1.71

Activations Density 1.212%

technical terms and brand/product names related to dietary supplements and health-related products

No Comments

No Known Activations