INDEX

Explanations

text related to instructions or procedures

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>

-3.10

ⓧ

-0.95

 intersper

-0.87

-0.76

/**

-0.73

 defray

-0.72

 AssemblyCompany

-0.70

 endow

-0.69

 inaugurate

-0.69

 harmonize

-0.69

POSITIVE LOGITS

 kafe

1.07

 karton

1.04

 silikon

1.02

uhr

1.01

 alkoh

0.97

 kado

0.95

 keramik

0.94

 kosme

0.92

 seksi

0.90

 kaos

0.90

Activations Density 0.298%

text related to instructions or procedures

No Comments

No Known Activations