INDEX

Explanations

connections between entities and possessive forms

oai_token-act-pair · gpt-3.5-turbo

possessive forms indicating ownership or association

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

ENN

-0.76

ording

-0.75

lehem

-0.75

cible

-0.75

BT

-0.75

KT

-0.74

—-

-0.74

dylib

-0.73

Els

-0.72

Ú

-0.71

POSITIVE LOGITS

 penchant

1.06

 biggest

1.02

 inability

1.01

 newest

0.95

 detractors

0.94

 unwillingness

0.93

 reluctance

0.92

 insistence

0.91

 fingerprints

0.91

 obsession

0.90

Activations Density 0.138%

connections between entities and possessive forms

possessive forms indicating ownership or association

No Comments

No Known Activations