INDEX

Explanations

complex or contrasting phrases

oai_token-act-pair · gpt-3.5-turbo

contrastive conjunctions and qualifiers that indicate complexity or nuance in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

mpeg

-0.86

ouses

-0.78

oku

-0.77

anners

-0.75

//[

-0.72

okemon

-0.72

ramids

-0.72

bos

-0.71

atari

-0.68

kees

-0.68

POSITIVE LOGITS

 unden

0.95

 unintentional

0.82

 economical

0.81

 effic

0.79

 unsur

0.78

 consequential

0.77

 unbiased

0.76

 unpop

0.76

 profitable

0.76

 uncom

0.75

Activations Density 0.220%

complex or contrasting phrases

contrastive conjunctions and qualifiers that indicate complexity or nuance in statements

No Comments

No Known Activations