INDEX

Explanations

phrases related to information accuracy and ethical considerations

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

 malheure

-0.99

 unwarran

-0.96

Wtf

-0.94

 shenan

-0.88

Ikr

-0.86

Yess

-0.84

Noice

-0.84

 disagre

-0.84

 Lmao

-0.83

 effray

-0.83

POSITIVE LOGITS

<bos>

1.05

 interesting

0.73

 story

0.64

interesting

0.63

sworth

0.61

 Himo

0.58

 interes

0.58

 fascinating

0.57

 juicy

0.56

 ContentValues

0.56

Activations Density 0.555%

phrases related to information accuracy and ethical considerations

No Comments

No Known Activations