INDEX

Explanations

information about specific locations, events, and activities

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>

-2.92

 disbur

-0.88

 endow

-0.85

ⓧ

-0.85

 gratify

-0.83

-0.81

 defray

-0.81

 ratify

-0.79

 subdue

-0.78

 banish

-0.78

POSITIVE LOGITS

 silikon

1.04

 karton

0.99

 kafe

0.98

 ananas

0.97

emmel

0.96

 marte

0.96

 bourg

0.93

 balkon

0.92

 échou

0.92

 cioc

0.91

Activations Density 0.080%

information about specific locations, events, and activities

No Comments

No Known Activations