INDEX

Explanations

phrases related to activities or processes that are currently in progress or ongoing

oai_token-act-pair · gpt-3.5-turbo

phrases related to ongoing processes or activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

raped

-0.67

pi

-0.66

ritical

-0.63

nie

-0.63

itri

-0.62

rug

-0.62

regate

-0.62

 Caps

-0.61

uable

-0.60

uci

-0.59

POSITIVE LOGITS

CLASSIFIED

0.75

 concurrently

0.75

 anew

0.73

 beforehand

0.71

 underway

0.69

insula

0.63

 HERE

0.63

 Caption

0.62

uberty

0.62

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.62

Activations Density 0.056%

phrases related to activities or processes that are currently in progress or ongoing

phrases related to ongoing processes or activities

No Comments

No Known Activations