INDEX

Explanations

words related to written correspondence or communication

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "letter."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rolet

-0.70

 Tune

-0.67

 CCTV

-0.67

negie

-0.67

 Occupations

-0.66

illon

-0.66

ESCO

-0.65

Nex

-0.61

imation

-0.61

alon

-0.61

POSITIVE LOGITS

Letter

0.95

 addressed

0.90

 letter

0.89

velop

0.87

letter

0.83

press

0.83

 memos

0.83

 penned

0.82

 letters

0.80

 sent

0.79

Activations Density 0.027%

words related to written correspondence or communication

occurrences of the word "letter."

No Comments

No Known Activations