INDEX

Explanations

descriptions of locations and events, possibly related to news or narratives

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

<bos>

-0.65

Điều

-0.60

Kết

-0.58

Và

-0.57

)$/,

-0.57

>({

-0.57

==""){

-0.56

ROIT

-0.56

ője

-0.56

\},

-0.56

POSITIVE LOGITS

 Gorb

1.44

 secon

1.43

 guarante

1.39

 depic

1.38

 intermitt

1.37

 Bartholo

1.36

 vété

1.35

 reluct

1.34

 impra

1.33

 inev

1.33

Activations Density 0.520%

descriptions of locations and events, possibly related to news or narratives

No Comments

No Known Activations