INDEX

Explanations

mentions of products, features, and benefits in text related to various industries and domains

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 panik

-1.09

 thuy

-1.03

 saar

-0.97

kac

-0.97

 kasa

-0.96

 Strukt

-0.92

 Kategor

-0.90

 meis

-0.90

 Kese

-0.88

 gymnas

-0.88

POSITIVE LOGITS

 tupperware

0.77

 ecru

0.72

 velour

0.70

 Dizziness

0.69

 nutella

0.64

 differentiable

0.63

 hairc

0.62

 mascarpone

0.61

 tufted

0.60

 paisley

0.60

Activations Density 0.237%

mentions of products, features, and benefits in text related to various industries and domains

No Comments

No Known Activations