INDEX

Explanations

phrases related to events, organizations, and apologies

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.38

styleType

-0.69

codehaus

-0.63

Dimethyl

-0.62

 взе

-0.62

SizeF

-0.61

HasIndex

-0.61

Iné

-0.61

Και

-0.60

ExtendWith

-0.60

POSITIVE LOGITS

 🤣🤣

1.21

Apo

1.17

 ?...

1.16

 Czechos

1.13

 😭😭

1.13

fta

1.12

 🥲

1.09

 increa

1.09

 🔥🔥

1.07

Apo

1.07

Activations Density 0.612%

phrases related to events, organizations, and apologies

No Comments

No Known Activations