INDEX

Explanations

information related to political figures and public opinion polling

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

 swarovski

-0.85

 ecru

-0.77

 murano

-0.74

 tricot

-0.72

 tupperware

-0.71

 nutella

-0.70

 époux

-0.68

 idolat

-0.67

 withal

-0.66

 friable

-0.66

POSITIVE LOGITS

 poll

0.91

 polls

0.89

 polling

0.85

 survey

0.82

 polled

0.82

 surveys

0.81

 surveyed

0.74

polls

0.65

survey

0.65

poll

0.65

Activations Density 0.250%

information related to political figures and public opinion polling

No Comments

No Known Activations