INDEX

Explanations

words related to political parties and historical figures

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

 affez

-0.86

 rispond

-0.79

<bos>

-0.76

 riemp

-0.75

 allarg

-0.73

 isolato

-0.72

<?

-0.71

🕗

-0.70

 cammin

-0.69

 dicono

-0.68

POSITIVE LOGITS

 strto

0.51

 Koning

0.49

0.47

ity

0.47

ism

0.46

ous

0.45

("")

0.45

0.44

(:)

0.43

’

0.43

Activations Density 0.927%

words related to political parties and historical figures

No Comments

No Known Activations