INDEX

Explanations

phrases related to personal experiences involving various activities or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "had" 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

bie

-0.69

bies

-0.67

bery

-0.63

 Below

-0.63

owe

-0.62

 Voters

-0.62

hack

-0.60

edy

-0.60

ethy

-0.58

yles

-0.56

POSITIVE LOGITS

 been

1.06

 gotten

0.99

 undergone

0.94

 begun

0.91

 gone

0.89

iths

0.82

 dealings

0.78

rontal

0.77

 done

0.77

 wandered

0.77

Activations Density 0.134%

phrases related to personal experiences involving various activities or events

occurrences of the word "had" in various contexts

No Comments

No Known Activations