INDEX

Explanations

names or entities related to the abbreviation "KA"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or entities

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

YING

-0.73

FACE

-0.73

ARDS

-0.71

dress

-0.63

 Chronicle

-0.62

PLIED

-0.62

 Penet

-0.60

Davis

-0.60

 Reaper

-0.60

Quality

-0.59

POSITIVE LOGITS

Lok

1.53

 Sabha

1.45

ataka

1.07

 Pradesh

1.07

opa

0.94

itte

0.91

olith

0.88

unda

0.86

otom

0.84

alore

0.83

Activations Density 0.005%

names or entities related to the abbreviation "KA"

mentions of specific individuals or entities

No Known Activations