INDEX

Explanations

phrases related to technical or instructional content, possibly explaining proper techniques or procedures

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

 Sarm

-0.63

 Pyrene

-0.63

 Middles

-0.62

 philanth

-0.60

 Heeren

-0.60

 Abbé

-0.56

 Hano

-0.56

 Philadel

-0.55

 emigrants

-0.55

 rasc

-0.55

POSITIVE LOGITS

archiviato

0.53

WriteBarrier

0.50

∖

0.48

 Wikimédia

0.46

omock

0.46

 AVEC

0.46

AddTagHelper

0.45

 custos

0.44

 مُعرِّف

0.44

Synonymes

0.44

Activations Density 0.155%

phrases related to technical or instructional content, possibly explaining proper techniques or procedures

No Comments

No Known Activations