INDEX

Explanations

proper nouns, particularly names of locations or people

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

-0.80

 depic

-0.80

 contex

-0.75

 embodi

-0.75

TheGreat

-0.75

 resear

-0.71

 pamph

-0.70

!".

-0.70

!”.

-0.69

 emphat

-0.69

POSITIVE LOGITS

 >=",

0.79

película

0.66

Αν

0.65

 <=",

0.63

municipi

0.62

Ótimo

0.61

Abraços

0.61

Από

0.60

Δείτε

0.59

<",

0.58

Activations Density 1.434%

proper nouns, particularly names of locations or people

No Comments

No Known Activations