INDEX

Explanations

references to a particular medical condition or medical company named "PD"

oai_token-act-pair · gpt-3.5-turbo

the occurrence of the abbreviation "PD" in various contexts

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

ppo

-0.92

hold

-0.86

bourg

-0.74

akia

-0.71

natureconservancy

-0.71

holding

-0.70

glers

-0.68

ansas

-0.68

Interstitial

-0.68

ishi

-0.67

POSITIVE LOGITS

iamond

0.97

ouble

0.92

GF

0.88

oodle

0.87

ATES

0.83

illon

0.83

PD

0.82

insula

0.81

iants

0.80

ynasty

0.79

Activations Density 0.023%

references to a particular medical condition or medical company named "PD"

the occurrence of the abbreviation "PD" in various contexts

No Comments

No Known Activations