INDEX

Explanations

references to specific events or things in a detailed text, such as names, locations, and historical information

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.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

<bos>

-1.25

Fordítás

-0.63

 września

-0.62

 Dlatego

-0.61

 Mónica

-0.60

CreateIndex

-0.59

 Bardzo

-0.59

 Bárbara

-0.59

 Darío

-0.59

 Belén

-0.58

POSITIVE LOGITS

Ca

1.07

 casio

0.93

Ca

0.89

 lara

0.89

 Calcium

0.88

 unce

0.87

 roth

0.84

 friable

0.84

 jessica

0.84

 jaya

0.84

Activations Density 0.584%

references to specific events or things in a detailed text, such as names, locations, and historical information

No Comments

No Known Activations