INDEX

Explanations

names and locations

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

 Hül

-1.40

 Wiking

-1.35

<bos>

-1.32

 Städ

-1.29

 Schloß

-1.20

 Händ

-1.16

 Stä

-1.14

 Flü

-1.10

 Segen

-1.09

zyn

-1.08

POSITIVE LOGITS

 Shakspeare

1.98

 Whence

1.92

 Confu

1.79

 disagre

1.78

fta

1.78

 unwarran

1.76

 Augu

1.75

 impra

1.73

 tolerably

1.72

ftu

1.70

Activations Density 0.532%

names and locations

No Comments

No Known Activations