INDEX

Explanations

references to the company or brand 'GM'

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>

-1.25

 intersper

-1.12

 chrysler

-1.08

 purcha

-1.06

 encomp

-1.05

 apprehen

-0.99

 outlander

-0.96

 reluct

-0.93

 indestru

-0.90

 strick

-0.89

POSITIVE LOGITS

GM

1.27

GM

1.23

gm

0.95

gm

0.93

UserScript

0.90

 saar

0.90

 miele

0.81

 maksi

0.75

 saad

0.74

=-=-

0.74

Activations Density 0.424%

references to the company or brand 'GM'

No Comments

No Known Activations