INDEX

Explanations

news articles about technology products and features

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Darum

-0.92

 explications

-0.83

BnF

-0.80

 Zwar

-0.79

Ihm

-0.75

 DELLE

-0.72

 Daß

-0.72

Assista

-0.72

 Endlich

-0.71

 CiNii

-0.69

POSITIVE LOGITS

The

0.72

Finally

0.71

This

0.69

<bos>

0.68

“:

0.67

Whether

0.66

For

0.65

Overall

0.65

When

0.64

If

0.64

Activations Density 0.253%

news articles about technology products and features

No Comments

No Known Activations