INDEX

Explanations

telecommunication-related terms

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

 canard

-0.58

 squatting

-0.46

 impati

-0.43

 cocked

-0.42

 savour

-0.42

 mutter

-0.41

 scorched

-0.41

 swarming

-0.41

 wack

-0.41

 Rust

-0.41

POSITIVE LOGITS

 tele

1.41

 Tele

1.37

Tele

1.33

 TELE

1.24

tele

1.23

TELE

1.09

 Télé

0.96

 télé

0.93

 Telecom

0.93

 telecom

0.92

Activations Density 0.078%

telecommunication-related terms

No Comments

No Known Activations