INDEX

Explanations

answers to questions and justifications

oai_token-act-pair · gpt-3.5-turbo

sentences that pose questions or provide explanations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

apixel

-0.85

 torch

-0.78

geon

-0.75

iership

-0.74

jer

-0.73

 stret

-0.73

handle

-0.71

alon

-0.71

usha

-0.71

wn

-0.70

POSITIVE LOGITS

ecause

0.90

 reasons

0.86

cause

0.80

Reason

0.80

======

0.80

Because

0.80

 jealousy

0.78

========

0.78

============

0.77

Cause

0.75

Activations Density 0.228%

answers to questions and justifications

sentences that pose questions or provide explanations

No Comments

No Known Activations