INDEX

Explanations

adjectives that describe emotional or qualitative states

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.12.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.02

/***

-0.99

///**

-0.79

-0.70

lateinit

-0.69

<?

-0.69

ⓧ

-0.63

<?

-0.63

 troviamo

-0.61

expandindo

-0.61

POSITIVE LOGITS

 chrysler

1.12

 Minang

1.07

 Jambi

1.04

 ecru

1.04

 hilux

1.01

 tupperware

0.96

 sceptre

0.96

 Whence

0.95

 Banjar

0.94

 réfugi

0.94

Activations Density 0.243%

adjectives that describe emotional or qualitative states

No Comments

No Known Activations