INDEX

Explanations

lowercase words starting with the letter "a"

oai_token-act-pair · gpt-3.5-turbo

the article "a" and its variations used in different contexts

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

AIDS

-0.80

votes

-0.75

Hon

-0.74

Events

-0.73

overs

-0.72

AFP

-0.72

Af

-0.72

America

-0.71

 gays

-0.71

 Orlando

-0.69

POSITIVE LOGITS

uras

1.10

lot

1.05

 bunch

1.02

 plethora

1.00

roma

1.00

 large

0.98

 separate

0.94

 multitude

0.94

 subset

0.92

 simplified

0.92

Activations Density 0.706%

lowercase words starting with the letter "a"

the article "a" and its variations used in different contexts

No Comments

No Known Activations