INDEX

Explanations

words related to physical characteristics, such as "shiny," and details about cooking ingredients and techniques

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.98

Více

-0.87

Iné

-0.77

Související

-0.76

Warto

-0.75

/***

-0.73

Zdroj

-0.73

Výhody

-0.72

<tfoot>

-0.71

POSITIVE LOGITS

aty

1.17

iny

1.16

amy

1.08

ety

1.06

edy

1.05

AMY

1.04

vy

1.03

 ordina

1.02

chy

1.02

VY

1.01

Activations Density 0.257%

words related to physical characteristics, such as "shiny," and details about cooking ingredients and techniques

No Comments

No Known Activations