INDEX

Explanations

relationships and interactions between different individuals

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

mef

-1.45

 dises

-1.41

 haup

-1.33

umo

-1.33

 gonz

-1.33

 seiz

-1.33

fordable

-1.31

 canel

-1.30

hcm

-1.28

 abnorm

-1.28

POSITIVE LOGITS

He

0.91

She

0.83

 They

0.82

 Thus

0.78

His

0.77

So

0.76

 Therefore

0.75

<eos>

0.75

↵↵

0.74

But

0.74

Activations Density 0.500%

relationships and interactions between different individuals

No Comments

No Known Activations