INDEX

Explanations

the word "using" followed by a technology or tool

oai_token-act-pair · gpt-3.5-turbo

instances of the word "using."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hra

-0.73

uberty

-0.68

 nerv

-0.67

 Mysteries

-0.66

naire

-0.65

oglu

-0.62

witz

-0.61

 Houth

-0.61

mortem

-0.60

cffffcc

-0.60

POSITIVE LOGITS

FUL

0.94

ience

0.85

fully

0.81

 aliases

0.77

 computers

0.76

fulness

0.75

iences

0.74

 condoms

0.73

full

0.71

 tools

0.70

Activations Density 0.079%

the word "using" followed by a technology or tool

instances of the word "using."

No Comments

No Known Activations