INDEX

Explanations

mentions of technical terms in a programming context

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

 ?...

-1.35

 desir

-1.33

 increa

-1.31

 volunte

-1.30

 encomp

-1.30

fuf

-1.29

 inev

-1.28

 effe

-1.26

 greate

-1.25

 alre

-1.25

POSITIVE LOGITS

 unless

1.06

 anymore

1.04

nor

1.00

unless

0.97

nor

0.79

 except

0.77

 sondern

0.75

except

0.74

 because

0.73

due

0.73

Activations Density 0.693%

mentions of technical terms in a programming context

No Comments

No Known Activations