INDEX

Explanations

indefinite articles

oai_token-act-pair · gpt-3.5-turbo

articles that introduce or highlight significant subjects or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

words

-0.75

coins

-0.71

tests

-0.70

 Acts

-0.66

Rules

-0.65

parts

-0.65

oons

-0.64

 aloud

-0.64

 Bars

-0.64

Edit

-0.63

POSITIVE LOGITS

lot

1.21

 plethora

1.17

 tremendous

1.09

 mixture

1.06

 bunch

1.05

 considerable

1.05

 glimpse

1.05

 huge

1.03

 sizeable

1.02

 tremend

1.01

Activations Density 0.332%

indefinite articles

articles that introduce or highlight significant subjects or objects

No Comments

No Known Activations