INDEX

Explanations

phrases starting with "the."

oai_token-act-pair · gpt-3.5-turbo

the definite article "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 with

-0.77

estate

-0.68

SHIP

-0.61

ãĥĺ

-0.60

 Rahul

-0.60

ECA

-0.60

NULL

-0.58

 according

-0.58

 however

-0.58

iffe

-0.57

POSITIVE LOGITS

 utmost

1.13

 remainder

1.02

 same

1.00

 slightest

0.98

 afore

0.97

 highest

0.94

 latter

0.92

ocratic

0.91

ses

0.91

 heaviest

0.91

Activations Density 0.240%

phrases starting with "the."

the definite article "the."

No Comments

No Known Activations