INDEX

Explanations

information about a specific topic, such as white tea, fishing policy, and ALS diagnosis, through instructional or informative text

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 burst

-0.90

 bursts

-0.69

burst

-0.62

 onPause

-0.60

Burst

-0.58

EqualsAnd

-0.57

 bursting

-0.56

 expand

-0.56

 Burst

-0.55

flich

-0.54

POSITIVE LOGITS

 overwhelming

1.92

whelming

1.41

 maroc

1.35

 stockholm

1.34

 lele

1.33

 meis

1.32

 oner

1.31

 ordina

1.30

fup

1.29

 wien

1.27

Activations Density 0.147%

information about a specific topic, such as white tea, fishing policy, and ALS diagnosis, through instructional or informative text

No Comments

No Known Activations