INDEX

Explanations

words related to reading or literacy

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

migrationBuilder

-0.54

MessageOf

-0.54

ganu

-0.53

WillAppear

-0.53

siębior

-0.53

Filmografia

-0.49

upuesto

-0.49

RetentionPolicy

-0.49

ties

-0.49

+#+

-0.48

POSITIVE LOGITS

 shenan

1.35

 unspeak

1.26

 increa

1.20

 read

1.19

 reluct

1.19

 misread

1.16

 apprehen

1.15

 snoopy

1.14

 horrend

1.13

 hairc

1.13

Activations Density 0.086%

words related to reading or literacy

No Comments

No Known Activations