INDEX

Explanations

mentions of political entities and decisions

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

 broderie

-0.95

 bandeau

-0.91

 flyknit

-0.85

 vété

-0.84

 Venise

-0.82

 chèvre

-0.82

 împre

-0.81

 Nguy

-0.79

 hoody

-0.78

 hairc

-0.77

POSITIVE LOGITS

 Heber

0.74

 Glou

0.67

 McDon

0.66

 Rine

0.64

 Burnet

0.64

 Franke

0.64

 Kild

0.64

 Harms

0.64

 Pott

0.63

 McLaugh

0.63

Activations Density 0.886%

mentions of political entities and decisions

No Comments

No Known Activations