INDEX

Explanations

actions or decisions taken by individuals

oai_token-act-pair · gpt-3.5-turbo

past tense verbs and actions indicating participation or engagement

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

artisan

-0.73

now

-0.69

udos

-0.69

arel

-0.69

HOW

-0.69

gel

-0.68

ibliography

-0.68

currently

-0.67

been

-0.66

vity

-0.66

POSITIVE LOGITS

 beforehand

0.74

nesday

0.73

 Doct

0.73

 last

0.65

 yesterday

0.65

 earlier

0.60

 Katrina

0.59

 unsuccessfully

0.58

 originally

0.58

Activations Density 0.543%

actions or decisions taken by individuals

past tense verbs and actions indicating participation or engagement

No Comments

No Known Activations