INDEX

Explanations

words related to simplification and simplifying processes

oai_token-act-pair · gpt-3.5-turbo

terms related to simplification

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

affer

-0.76

EP

-0.69

 fertile

-0.66

hips

-0.65

Grant

-0.64

entin

-0.64

CVE

-0.63

vine

-0.63

 eminent

-0.63

âĻ¦

-0.62

POSITIVE LOGITS

 simpl

1.02

 simplify

0.97

 Simpl

0.94

 simplified

0.89

 simplicity

0.88

simple

0.85

 simpler

0.80

Catalog

0.78

ifies

0.76

 inconven

0.74

Activations Density 0.018%

words related to simplification and simplifying processes

terms related to simplification

No Comments

No Known Activations