INDEX

Explanations

words related to important events or critical decisions

oai_token-act-pair · gpt-3.5-turbo

words related to critical moments or decisions

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

Negative Logits

rug

-0.86

erves

-0.82

folk

-0.78

psc

-0.77

gas

-0.73

flix

-0.72

lance

-0.72

spe

-0.71

children

-0.71

inav

-0.71

POSITIVE LOGITS

onite

0.86

jun

0.84

 moment

0.83

 showdown

0.83

 moments

0.83

 swing

0.82

 blow

0.79

 battle

0.79

 battleground

0.78

 adolesc

0.77

Activations Density 0.050%

words related to important events or critical decisions

words related to critical moments or decisions

No Known Activations