INDEX

Explanations

mathematical and numerical terms or concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to statistics, measurements, and economic values

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

rahim

-0.68

èĪ

-0.68

enda

-0.66

 Honour

-0.65

çīĪ

-0.65

hops

-0.64

inia

-0.64

inka

-0.63

NetMessage

-0.63

orea

-0.63

POSITIVE LOGITS

 difference

1.03

 allowable

0.99

 discrepancy

0.92

liest

0.88

 portion

0.87

 differential

0.86

 payable

0.84

of

0.84

 computation

0.82

 ceiling

0.81

Activations Density 0.205%

mathematical and numerical terms or concepts

terms related to statistics, measurements, and economic values

No Comments

No Known Activations