INDEX

Explanations

references to monetary amounts

oai_token-act-pair · gpt-3.5-turbo

monetary values or salary information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

hess

-0.69

 Journals

-0.69

acebook

-0.66

tal

-0.66

 Ging

-0.64

acid

-0.63

forth

-0.61

NK

-0.61

ingly

-0.61

Edit

-0.60

POSITIVE LOGITS

 month

1.07

 week

1.06

 year

1.01

decade

0.92

day

0.92

 couple

0.90

 fortnight

0.88

 single

0.85

 gallon

0.83

 piece

0.82

Activations Density 0.042%

references to monetary amounts

monetary values or salary information

No Comments

No Known Activations