INDEX

Explanations

phrases where someone or something is identified or described in a specific way

oai_token-act-pair · gpt-3.5-turbo

phrases that describe relationships or connections between entities

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

Oo

-0.72

vantage

-0.62

cel

-0.61

 Ragnarok

-0.60

role

-0.60

rom

-0.60

 Refresh

-0.59

oom

-0.59

Marvel

-0.58

 laughed

-0.58

POSITIVE LOGITS

Detailed

0.79

ATIONAL

0.73

ADRA

0.71

erity

0.71

yip

0.69

ĸļ

0.69

vernment

0.69

¿½

0.68

ignt

0.68

lain

0.67

Activations Density 0.730%

phrases where someone or something is identified or described in a specific way

phrases that describe relationships or connections between entities

No Comments

No Known Activations