INDEX

Explanations

mention of the most recent or up-to-date information in a variety of contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "recent" 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

qqa

-0.80

İĭ

-0.74

avery

-0.73

wyn

-0.71

ñ

-0.70

rats

-0.70

cius

-0.70

cca

-0.69

isha

-0.69

max

-0.66

POSITIVE LOGITS

 incarnation

1.00

 installment

0.97

 iteration

0.90

 edition

0.89

 episode

0.89

 installments

0.81

 occupant

0.80

 iterations

0.77

 editions

0.77

 episodes

0.77

Activations Density 0.013%

mention of the most recent or up-to-date information in a variety of contexts

occurrences of the word "recent" in various contexts

No Comments

No Known Activations