INDEX

Explanations

words related to actions or events happening in the past

oai_token-act-pair · gpt-3.5-turbo

the verb "saw" and its variations in different contexts

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

 contrace

-0.78

externalActionCode

-0.69

 agric

-0.67

Newsletter

-0.66

trap

-0.66

 Tanz

-0.65

 Adin

-0.63

 shotgun

-0.63

PHOTOS

-0.61

 Sett

-0.60

POSITIVE LOGITS

awed

0.97

Ĺ

0.94

arnaev

0.83

eeper

0.82

dust

0.80

ei

0.78

lights

0.77

ered

0.77

rov

0.73

 visions

0.72

Activations Density 0.078%

words related to actions or events happening in the past

the verb "saw" and its variations in different contexts

No Comments

No Known Activations