INDEX

Explanations

words related to political tension and high stakes situations, potentially in the context of political leaders and elections

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

 reluct

-1.05

ftu

-1.01

 apprehen

-0.96

 increa

-0.96

 disagre

-0.95

 desir

-0.95

fta

-0.94

 depic

-0.94

 nece

-0.93

 unlaw

-0.93

POSITIVE LOGITS

 stakes

0.85

stakes

0.68

 importance

0.67

 Stakes

0.67

IsContent

0.64

 stake

0.63

 implications

0.63

importance

0.59

 decisions

0.59

 consequences

0.57

Activations Density 0.518%

words related to political tension and high stakes situations, potentially in the context of political leaders and elections

No Comments

No Known Activations