INDEX

Explanations

references to robots, robotics, and related technologies

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>

-2.01

HideFlags

-0.64

 sniffed

-0.55

 renounced

-0.54

 relinquished

-0.53

uresh

-0.52

 rejoined

-0.52

 pierce

-0.51

 snapped

-0.51

 scooped

-0.50

POSITIVE LOGITS

 robot

1.25

robot

1.11

 robots

1.10

Robot

1.09

Robots

1.08

 Robot

1.08

bot

1.05

Bots

1.04

 Bots

1.04

robots

1.04

Activations Density 0.190%

references to robots, robotics, and related technologies

No Comments

No Known Activations