INDEX

Explanations

references to specific periods of time or durations

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

 kwiet

-0.72

 Hinblick

-0.68

 ziua

-0.63

 Secrétaire

-0.61

 tanong

-0.60

idać

-0.59

 betreff

-0.59

zondere

-0.57

 huwa

-0.56

ypeł

-0.55

POSITIVE LOGITS

 robus

0.83

 abnorm

0.82

Eks

0.77

 Amerik

0.77

 unan

0.74

 Rektor

0.74

 Senat

0.73

 Verk

0.73

 Vorm

0.73

 praktik

0.73

Activations Density 0.086%

references to specific periods of time or durations

No Comments

No Known Activations