INDEX

Explanations

proper nouns or specific terms, potentially related to products or locations

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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

Ka

-0.60

otheby

-0.56

criptures

-0.55

ColumnHeaders

-0.53

icznego

-0.51

tangentMode

-0.51

 defaultstate

-0.50

underland

-0.50

 emissions

-0.49

IGraphics

-0.49

POSITIVE LOGITS

ka

1.94

KA

1.29

ftu

1.21

 sovere

1.18

 stockholm

1.18

 tranf

1.16

 reft

1.14

 sappi

1.11

 perfon

1.11

 nece

1.10

Activations Density 0.191%

proper nouns or specific terms, potentially related to products or locations

No Comments

No Known Activations