INDEX

Explanations

references to written reminders or notes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "memo."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

reek

-0.66

ulia

-0.66

alien

-0.65

adjusted

-0.64

places

-0.64

Interstitial

-0.63

 Tune

-0.62

gain

-0.61

gpu

-0.61

Fen

-0.60

POSITIVE LOGITS

andum

1.12

 memo

1.03

ographed

0.88

osal

0.88

 memos

0.87

isode

0.84

 outlining

0.82

izational

0.81

ufact

0.81

velop

0.81

Activations Density 0.030%

references to written reminders or notes

occurrences of the word "memo."

No Comments

No Known Activations