INDEX

Explanations

phrases related to concealing identity and leading back to someone

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

 kosme

-0.70

 quæ

-0.67

 Sén

-0.67

 minimalis

-0.67

 akut

-0.65

 panik

-0.63

 konserv

-0.63

 kapital

-0.63

Cfr

-0.62

 antik

-0.62

POSITIVE LOGITS

 identification

0.76

 identify

0.70

 identifying

0.70

 Identifying

0.66

 Identification

0.66

 identifier

0.65

identify

0.64

Identifying

0.64

 traceability

0.62

 Identify

0.61

Activations Density 0.379%

phrases related to concealing identity and leading back to someone

No Comments

No Known Activations