INDEX

Explanations

specific words related to a particular game or products of a game company

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>

-2.52

InvalidProtocol

-0.69

 Obrador

-0.68

ItemBackground

-0.68

 autorytatywna

-0.68

 geldig

-0.67

TargetException

-0.66

mtable

-0.66

 gyhoeddwyd

-0.65

 Paglinawan

-0.65

POSITIVE LOGITS

 increa

1.70

Juf

1.63

 suscep

1.61

 disagre

1.60

 emphat

1.57

 impra

1.56

 BETA

1.55

 unden

1.49

 effe

1.49

 thut

1.49

Activations Density 0.319%

specific words related to a particular game or products of a game company

No Comments

No Known Activations