INDEX

Explanations

references to written communication in the form of letters

oai_token-act-pair · gpt-3.5-turbo

references to letters or written correspondence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AMD

-0.69

run

-0.66

cosystem

-0.65

imate

-0.65

stable

-0.65

¥µ

-0.64

tackle

-0.62

mob

-0.62

 Grab

-0.62

moderate

-0.61

POSITIVE LOGITS

 letters

3.90

 Letters

2.78

 letter

2.62

letters

2.33

letter

2.16

Letter

2.10

 Letter

2.09

 correspondence

1.82

 memos

1.57

 emails

1.54

Activations Density 0.019%

references to written communication in the form of letters

references to letters or written correspondence

No Comments

No Known Activations