INDEX

Explanations

words related to making changes or modifications

oai_token-act-pair · gpt-3.5-turbo

terms related to adjustment, accommodation, and improvement 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

alam

-0.64

................................................................

-0.64

ãģ®

-0.63

 squared

-0.62

pmwiki

-0.60

antam

-0.60

 Exhibit

-0.59

................................

-0.56

 href

-0.55

 Absent

-0.55

POSITIVE LOGITS

uate

0.83

itial

0.74

 maxim

0.67

 conversions

0.66

 maximum

0.66

MAT

0.66

balance

0.63

romptu

0.63

 redundancy

0.62

enance

0.62

Activations Density 0.290%

words related to making changes or modifications

terms related to adjustment, accommodation, and improvement in various contexts

No Comments

No Known Activations