INDEX

Explanations

mentions of the word "the" followed by another word starting with "he"

oai_token-act-pair · gpt-3.5-turbo

the pronoun "he" in various 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

hips

-0.89

 eleph

-0.78

 GEAR

-0.69

 linking

-0.64

 domestically

-0.63

 gearing

-0.60

 Labrador

-0.60

 gems

-0.60

 correlation

-0.59

 unfocusedRange

-0.58

POSITIVE LOGITS

isure

1.13

atre

1.05

lling

0.99

ller

0.98

aven

0.97

aton

0.96

ALTH

0.94

ather

0.93

gan

0.93

brew

0.93

Activations Density 0.057%

mentions of the word "the" followed by another word starting with "he"

the pronoun "he" in various contexts

No Comments

No Known Activations