INDEX

Explanations

names or terms related to a specific individual or organization

oai_token-act-pair · gpt-3.5-turbo

mentions of the term 'ge' 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

kefeller

-0.94

icum

-0.89

acca

-0.87

Interstitial

-0.75

ities

-0.72

idental

-0.68

ABE

-0.67

umenthal

-0.66

ishment

-0.65

aptic

-0.65

POSITIVE LOGITS

orge

1.04

hog

1.03

ORGE

0.97

rer

0.88

cko

0.81

 Warfare

0.81

rers

0.81

orgetown

0.81

ois

0.80

eks

0.79

Activations Density 0.035%

names or terms related to a specific individual or organization

mentions of the term 'ge' in various contexts

No Comments

No Known Activations