INDEX

Explanations

and highlight phrases denoting the significant size or extent of something

oai_token-act-pair · gpt-3.5-turbo

terms related to the magnitude or scale of issues and challenges

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

inis

-0.77

isse

-0.71

Eva

-0.71

arna

-0.71

Pic

-0.70

IAS

-0.69

vant

-0.69

iku

-0.68

yne

-0.67

ategor

-0.67

POSITIVE LOGITS

 extent

0.76

 similarities

0.75

of

0.74

 nature

0.74

 similarity

0.73

 inherent

0.71

 amount

0.71

 unfolding

0.70

 uniqueness

0.68

iest

0.68

Activations Density 0.254%

and highlight phrases denoting the significant size or extent of something

terms related to the magnitude or scale of issues and challenges

No Comments

No Known Activations