INDEX

Explanations

movie titles

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.15

guang

-0.70

sheng

-0.66

fillType

-0.64

qiao

-0.61

yao

-0.61

zhong

-0.58

springframework

-0.57

묶

-0.56

usercontent

-0.56

POSITIVE LOGITS

 affor

1.51

 indestru

1.48

 unwarran

1.39

 maneu

1.38

 LXXX

1.36

 increa

1.35

 scrat

1.35

 perfet

1.35

 excru

1.35

 emphat

1.34

Activations Density 0.484%

movie titles

No Comments

No Known Activations