INDEX

Explanations

phrases related to patronage or support

oai_token-act-pair · gpt-3.5-turbo

terms related to patrons and patronage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

nesota

-0.78

grass

-0.69

binding

-0.68

LOD

-0.68

RN

-0.67

Course

-0.66

sg

-0.65

trap

-0.65

scape

-0.65

REE

-0.65

POSITIVE LOGITS

isance

1.03

 patrons

0.95

hetically

0.92

 patron

0.91

 saint

0.88

iless

0.80

ysis

0.80

 Patron

0.80

atern

0.75

umeric

0.72

Activations Density 0.030%

phrases related to patronage or support

terms related to patrons and patronage

No Comments

No Known Activations