INDEX

Explanations

phrases related to controversial political events or statements

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

 Keny

-0.97

 Sted

-0.95

 kram

-0.88

 panik

-0.88

 Intere

-0.85

 abnorm

-0.83

Nö

-0.81

Juf

-0.79

 Teks

-0.79

 Miscell

-0.79

POSITIVE LOGITS

 😭😭

0.60

 velkommen

0.60

 vrea

0.57

as

0.56

 drept

0.56

 vedea

0.56

 виправи

0.55

dă

0.54

Ці

0.53

 gezet

0.51

Activations Density 0.484%

phrases related to controversial political events or statements

No Comments

No Known Activations