INDEX

Explanations

terms related to change or transformation

oai_token-act-pair · gpt-3.5-turbo

terms related to change or transformation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PRES

-0.71

olicited

-0.69

 Physicians

-0.68

PLIED

-0.67

ä½ľ

-0.67

Ô

-0.66

AMS

-0.65

QUEST

-0.65

©¶æ

-0.65

RAY

-0.64

POSITIVE LOGITS

 chang

1.50

eless

1.00

 breaker

0.84

xual

0.83

eworthy

0.82

ials

0.77

 shif

0.76

ank

0.74

 strugg

0.74

ethe

0.72

Activations Density 0.004%

terms related to change or transformation

terms related to change or transformation

No Comments

No Known Activations