INDEX

Explanations

passive voice constructions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "were" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 sidx

-0.78

Ago

-0.72

 Awakens

-0.69

 Alone

-0.65

 reminds

-0.61

ITS

-0.61

ividual

-0.61

 Invention

-0.59

Lol

-0.59

 Dragonbound

-0.59

POSITIVE LOGITS

ŃĶ

1.05

ģ«

0.90

 abound

0.87

 underway

0.82

Ļ½

0.77

 available

0.77

©¶æ

0.77

ĺħ

0.73

 forthcoming

0.73

allowed

0.73

Activations Density 0.480%

passive voice constructions

occurrences of the word "were" and its variations

No Comments

No Known Activations