INDEX

Explanations

IP addresses

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "IP."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

tenance

-0.87

bourg

-0.83

ãĤ£

-0.77

ãĤ¡

-0.76

é¾įåĸļå£«

-0.76

 Cause

-0.76

brate

-0.75

enegger

-0.75

 Dying

-0.73

 Barcl

-0.73

POSITIVE LOGITS

ython

1.23

FW

0.83

raid

0.82

Os

0.81

 address

0.79

rint

0.76

osition

0.75

fen

0.75

terness

0.74

 infringement

0.73

Activations Density 0.012%

IP addresses

occurrences of the term "IP."

No Comments

No Known Activations