INDEX

Explanations

user comments and interactions on social media platforms

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

 makro

-1.75

 utop

-1.58

 moza

-1.57

 gesta

-1.47

hek

-1.47

 plak

-1.47

 solidar

-1.47

 gero

-1.47

 elek

-1.47

 adal

-1.44

POSITIVE LOGITS

 pamph

1.84

 unwarran

1.78

 unlaw

1.72

 tolerably

1.69

 impractica

1.64

 ecru

1.62

 hairc

1.62

 Ename

1.60

 disagre

1.59

 liberality

1.59

Activations Density 0.419%

user comments and interactions on social media platforms

No Comments

No Known Activations