INDEX

Explanations

references to family dynamics and personal relationships, particularly focusing on expectations and disappointments

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hcm

-1.45

 lele

-1.40

umo

-1.37

 levis

-1.37

 tanga

-1.33

 siena

-1.32

 kasa

-1.32

 kani

-1.31

 tulum

-1.31

mef

-1.29

POSITIVE LOGITS

 want

1.04

 wants

0.94

 wanted

0.88

 believe

0.88

 believes

0.82

 prefer

0.81

want

0.80

 desire

0.78

 wanting

0.78

 believed

0.76

Activations Density 0.398%

references to family dynamics and personal relationships, particularly focusing on expectations and disappointments

No Comments

No Known Activations