INDEX

Explanations

comparisons in various contexts

oai_token-act-pair · gpt-3.5-turbo

the word "to" and its associated phrases or values in comparative 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

iband

-0.76

ANCE

-0.73

Invalid

-0.71

DEN

-0.70

BRE

-0.68

awar

-0.64

tun

-0.64

WIND

-0.62

BSD

-0.62

colo

-0.62

POSITIVE LOGITS

 ours

0.77

 previous

0.76

 usual

0.76

 peers

0.75

 other

0.74

ggles

0.73

 those

0.68

 others

0.67

othy

0.64

 traditional

0.64

Activations Density 0.068%

comparisons in various contexts

the word "to" and its associated phrases or values in comparative contexts

No Comments

No Known Activations