INDEX

Explanations

mentions of specific legal acts or political 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

 guma

-0.63

 kani

-0.63

 saka

-0.58

 makita

-0.58

Mga

-0.58

 ilang

-0.57

 Middles

-0.57

naa

-0.55

kuu

-0.54

 kayo

-0.53

POSITIVE LOGITS

pat

1.36

Pat

1.36

Pat

1.35

pat

1.30

PAT

1.26

PAT

1.18

 Pats

0.97

Patricia

0.87

 pats

0.85

 Patt

0.80

Activations Density 0.071%

mentions of specific legal acts or political figures

No Comments

No Known Activations