INDEX

Explanations

comparisons between two different perspectives or sides

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

 unlaw

-1.21

 reluct

-1.15

 impractica

-1.12

 McLaugh

-1.10

 Shakspeare

-1.09

Juf

-1.08

 tolerably

-1.08

 unspeak

-1.07

 unwarran

-1.07

 Gorb

-1.05

POSITIVE LOGITS

<bos>

0.69

 side

0.63

side

0.57

Occasion

0.53

 behalf

0.53

ieR

0.53

 andererseits

0.52

 occasion

0.51

 occasions

0.50

 Bourgoin

0.48

Activations Density 0.082%

comparisons between two different perspectives or sides

No Comments

No Known Activations