INDEX

Explanations

the word "of" in different contexts and phrases

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "none"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

selves

-0.63

inem

-0.60

lees

-0.60

 tailor

-0.59

dayName

-0.58

 redesign

-0.58

bsite

-0.54

racuse

-0.53

rosis

-0.52

isoft

-0.52

POSITIVE LOGITS

 whatsoever

0.93

these

0.89

us

0.89

ahu

0.84

 these

0.83

course

0.81

them

0.81

those

0.79

¶æ

0.78

 them

0.73

Activations Density 0.043%

the word "of" in different contexts and phrases

occurrences of the word "none"

No Comments

No Known Activations