INDEX

Explanations

negative statements or contrasts

oai_token-act-pair · gpt-3.5-turbo

negative phrases and concepts regarding evidence and social issues

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

igm

-0.77

ipeg

-0.74

ovember

-0.66

 Nare

-0.65

iatus

-0.64

WN

-0.64

uden

-0.63

affe

-0.62

 Shan

-0.62

Notes

-0.61

POSITIVE LOGITS

asso

0.69

cause

0.66

 decency

0.64

 clot

0.63

 slightest

0.63

la

0.61

ilings

0.60

 hypocr

0.59

 sensit

0.57

 righteousness

0.57

Activations Density 0.261%

negative statements or contrasts

negative phrases and concepts regarding evidence and social issues

No Comments

No Known Activations