INDEX

Explanations

words relating to operations or operational tasks

oai_token-act-pair · gpt-3.5-turbo

occurrences of the root word "oper," likely relating to operations or functioning processes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

fix

-0.73

eree

-0.71

Ĥª

-0.68

 vengeance

-0.68

definition

-0.64

 haste

-0.63

 Primordial

-0.61

 blame

-0.60

ered

-0.60

xual

-0.59

POSITIVE LOGITS

aquin

0.94

atives

0.90

oper

0.86

ating

0.86

atively

0.86

ates

0.82

ately

0.81

ament

0.80

aqu

0.79

ational

0.79

Activations Density 0.008%

words relating to operations or operational tasks

occurrences of the root word "oper," likely relating to operations or functioning processes

No Known Activations