INDEX

Explanations

text encodings likely representing various data types or metadata within a larger body of content

oai_token-act-pair · gpt-3.5-turbo

instances of high numerical values or financial figures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oun

-0.96

 metic

-0.87

ĸļ

-0.86

 stem

-0.86

 nerv

-0.85

 smugglers

-0.83

 Ceres

-0.82

tyr

-0.80

 laure

-0.78

 spiral

-0.77

POSITIVE LOGITS

Examples

1.47

Use

1.46

Prov

1.45

Using

1.45

Performance

1.44

Ability

1.43

Similarly

1.43

Individual

1.42

Weak

1.41

Example

1.41

Activations Density 0.265%

text encodings likely representing various data types or metadata within a larger body of content

instances of high numerical values or financial figures

No Comments

No Known Activations