INDEX

Explanations

the word "accessible" in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "accessible" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nance

-0.74

chief

-0.74

protein

-0.71

origin

-0.70

hun

-0.69

ortium

-0.68

 Origin

-0.68

hunter

-0.67

stal

-0.64

und

-0.64

POSITIVE LOGITS

accessible

1.14

 accessible

1.07

ibility

0.98

ible

0.88

izable

0.86

isable

0.78

 accessibility

0.76

ahime

0.74

ebted

0.74

 inaccessible

0.74

Activations Density 0.005%

the word "accessible" in various contexts

instances of the word "accessible" in various contexts

No Comments

No Known Activations