INDEX

Explanations

specific mentions of "the" before a noun

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

âĢł

-0.77

:-)

-0.76

SPONSORED

-0.76

cules

-0.73

:)

-0.71

reve

-0.70

ersed

-0.68

ÅĤ

-0.68

pers

-0.66

ingly

-0.66

POSITIVE LOGITS

 league

1.20

 toughest

1.13

 same

1.11

 quickest

1.08

 playoffs

1.07

 postseason

1.04

 latter

1.03

 offseason

1.02

 scrimmage

1.02

 fastest

1.00

Activations Density 0.642%

specific mentions of "the" before a noun

occurrences of the word "the."

No Comments

No Known Activations