INDEX

Explanations

terms related to historical and geographical references

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

 estekak

-0.87

 OMIT

-0.77

migrationBuilder

-0.77

 doInBackground

-0.76

 <>",

-0.75

 referenties

-0.75

 Himo

-0.73

 klip

-0.73

cinogenicity

-0.71

rungsseite

-0.71

POSITIVE LOGITS

 unspeak

1.49

 indestru

1.41

 indescri

1.40

 intersper

1.39

 Whence

1.37

 reluct

1.32

 disagre

1.31

 inconce

1.30

 encomp

1.29

 depic

1.28

Activations Density 0.279%

terms related to historical and geographical references

No Comments

No Known Activations