INDEX

Explanations

the word "haven" in different contexts or forms such as "haven't"

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

 Cuer

-0.52

 Justo

-0.49

 granada

-0.45

 Leal

-0.44

 Robb

-0.43

Hvad

-0.43

Dermott

-0.43

 Rosales

-0.43

Dowell

-0.42

weebly

-0.42

POSITIVE LOGITS

 haven

0.84

 îna

0.82

haven

0.77

 intitulée

0.74

Haven

0.74

 Haven

0.73

:,,

0.73

;;)

0.72

.-"

0.71

 sarili

0.70

Activations Density 0.039%

the word "haven" in different contexts or forms such as "haven't"

No Comments

No Known Activations